1 line
117 KiB
JSON
1 line
117 KiB
JSON
[{"env_step": 0, "rew": -39.7281, "rew_std": 1.6637, "Agent": "PPO"}, {"env_step": 30720, "rew": -25.1977, "rew_std": 1.9758, "Agent": "PPO"}, {"env_step": 61440, "rew": -11.3756, "rew_std": 0.5121, "Agent": "PPO"}, {"env_step": 92160, "rew": -9.4285, "rew_std": 0.4521, "Agent": "PPO"}, {"env_step": 122880, "rew": -5.9949, "rew_std": 1.0133, "Agent": "PPO"}, {"env_step": 153600, "rew": -6.0315, "rew_std": 0.4946, "Agent": "PPO"}, {"env_step": 184320, "rew": -6.1742, "rew_std": 0.5615, "Agent": "PPO"}, {"env_step": 215040, "rew": -6.3098, "rew_std": 0.9039, "Agent": "PPO"}, {"env_step": 245760, "rew": -5.5179, "rew_std": 0.5696, "Agent": "PPO"}, {"env_step": 276480, "rew": -6.2265, "rew_std": 1.0758, "Agent": "PPO"}, {"env_step": 307200, "rew": -5.0218, "rew_std": 0.5475, "Agent": "PPO"}, {"env_step": 337920, "rew": -5.4688, "rew_std": 0.5576, "Agent": "PPO"}, {"env_step": 368640, "rew": -5.8007, "rew_std": 0.5325, "Agent": "PPO"}, {"env_step": 399360, "rew": -5.4248, "rew_std": 0.4431, "Agent": "PPO"}, {"env_step": 430080, "rew": -5.3748, "rew_std": 0.5162, "Agent": "PPO"}, {"env_step": 460800, "rew": -4.9695, "rew_std": 0.3465, "Agent": "PPO"}, {"env_step": 491520, "rew": -5.0357, "rew_std": 0.4891, "Agent": "PPO"}, {"env_step": 522240, "rew": -5.5683, "rew_std": 0.8495, "Agent": "PPO"}, {"env_step": 552960, "rew": -5.3753, "rew_std": 0.4371, "Agent": "PPO"}, {"env_step": 583680, "rew": -5.884, "rew_std": 0.4708, "Agent": "PPO"}, {"env_step": 614400, "rew": -5.5962, "rew_std": 0.3539, "Agent": "PPO"}, {"env_step": 645120, "rew": -5.3307, "rew_std": 0.4992, "Agent": "PPO"}, {"env_step": 675840, "rew": -6.0082, "rew_std": 0.9148, "Agent": "PPO"}, {"env_step": 706560, "rew": -5.2822, "rew_std": 0.4585, "Agent": "PPO"}, {"env_step": 737280, "rew": -4.7864, "rew_std": 0.7392, "Agent": "PPO"}, {"env_step": 768000, "rew": -5.0164, "rew_std": 0.3031, "Agent": "PPO"}, {"env_step": 798720, "rew": -5.3032, "rew_std": 0.5742, "Agent": "PPO"}, {"env_step": 829440, "rew": -5.1033, "rew_std": 0.3818, "Agent": "PPO"}, {"env_step": 860160, "rew": -5.3432, "rew_std": 0.8027, "Agent": "PPO"}, {"env_step": 890880, "rew": -4.6837, "rew_std": 0.5437, "Agent": "PPO"}, {"env_step": 921600, "rew": -4.7674, "rew_std": 0.3104, "Agent": "PPO"}, {"env_step": 952320, "rew": -4.1239, "rew_std": 0.3437, "Agent": "PPO"}, {"env_step": 983040, "rew": -4.595, "rew_std": 0.5033, "Agent": "PPO"}, {"env_step": 1013760, "rew": -4.9547, "rew_std": 0.5945, "Agent": "PPO"}, {"env_step": 1044480, "rew": -4.4337, "rew_std": 0.5052, "Agent": "PPO"}, {"env_step": 1075200, "rew": -4.6478, "rew_std": 0.377, "Agent": "PPO"}, {"env_step": 1105920, "rew": -4.6753, "rew_std": 0.5188, "Agent": "PPO"}, {"env_step": 1136640, "rew": -4.7786, "rew_std": 0.5445, "Agent": "PPO"}, {"env_step": 1167360, "rew": -4.7328, "rew_std": 0.5834, "Agent": "PPO"}, {"env_step": 1198080, "rew": -4.5149, "rew_std": 0.3676, "Agent": "PPO"}, {"env_step": 1228800, "rew": -4.8816, "rew_std": 0.402, "Agent": "PPO"}, {"env_step": 1259520, "rew": -5.1436, "rew_std": 0.4365, "Agent": "PPO"}, {"env_step": 1290240, "rew": -4.668, "rew_std": 0.3933, "Agent": "PPO"}, {"env_step": 1320960, "rew": -5.2896, "rew_std": 0.8658, "Agent": "PPO"}, {"env_step": 1351680, "rew": -4.5049, "rew_std": 0.5145, "Agent": "PPO"}, {"env_step": 1382400, "rew": -4.1827, "rew_std": 0.3268, "Agent": "PPO"}, {"env_step": 1413120, "rew": -4.3491, "rew_std": 0.8491, "Agent": "PPO"}, {"env_step": 1443840, "rew": -3.6947, "rew_std": 0.3381, "Agent": "PPO"}, {"env_step": 1474560, "rew": -4.4419, "rew_std": 0.3714, "Agent": "PPO"}, {"env_step": 1505280, "rew": -4.3424, "rew_std": 0.4925, "Agent": "PPO"}, {"env_step": 1536000, "rew": -4.2711, "rew_std": 0.2769, "Agent": "PPO"}, {"env_step": 1566720, "rew": -4.6186, "rew_std": 0.4963, "Agent": "PPO"}, {"env_step": 1597440, "rew": -4.625, "rew_std": 0.2289, "Agent": "PPO"}, {"env_step": 1628160, "rew": -4.3231, "rew_std": 0.4513, "Agent": "PPO"}, {"env_step": 1658880, "rew": -4.1184, "rew_std": 0.4354, "Agent": "PPO"}, {"env_step": 1689600, "rew": -4.4786, "rew_std": 0.4347, "Agent": "PPO"}, {"env_step": 1720320, "rew": -3.823, "rew_std": 0.4088, "Agent": "PPO"}, {"env_step": 1751040, "rew": -4.5142, "rew_std": 0.5797, "Agent": "PPO"}, {"env_step": 1781760, "rew": -3.9392, "rew_std": 0.4262, "Agent": "PPO"}, {"env_step": 1812480, "rew": -4.455, "rew_std": 0.3795, "Agent": "PPO"}, {"env_step": 1843200, "rew": -4.309, "rew_std": 0.3757, "Agent": "PPO"}, {"env_step": 1873920, "rew": -4.4861, "rew_std": 0.4123, "Agent": "PPO"}, {"env_step": 1904640, "rew": -3.8674, "rew_std": 0.2822, "Agent": "PPO"}, {"env_step": 1935360, "rew": -3.7656, "rew_std": 0.438, "Agent": "PPO"}, {"env_step": 1966080, "rew": -4.5965, "rew_std": 0.3614, "Agent": "PPO"}, {"env_step": 1996800, "rew": -3.847, "rew_std": 0.3441, "Agent": "PPO"}, {"env_step": 2027520, "rew": -4.1442, "rew_std": 0.2726, "Agent": "PPO"}, {"env_step": 2058240, "rew": -4.81, "rew_std": 0.5441, "Agent": "PPO"}, {"env_step": 2088960, "rew": -4.489, "rew_std": 0.3588, "Agent": "PPO"}, {"env_step": 2119680, "rew": -4.6354, "rew_std": 0.3608, "Agent": "PPO"}, {"env_step": 2150400, "rew": -4.8927, "rew_std": 0.3568, "Agent": "PPO"}, {"env_step": 2181120, "rew": -4.9722, "rew_std": 0.3395, "Agent": "PPO"}, {"env_step": 2211840, "rew": -3.9921, "rew_std": 0.4937, "Agent": "PPO"}, {"env_step": 2242560, "rew": -4.8395, "rew_std": 0.5691, "Agent": "PPO"}, {"env_step": 2273280, "rew": -4.2018, "rew_std": 0.2426, "Agent": "PPO"}, {"env_step": 2304000, "rew": -4.9258, "rew_std": 0.4614, "Agent": "PPO"}, {"env_step": 2334720, "rew": -4.4081, "rew_std": 0.2367, "Agent": "PPO"}, {"env_step": 2365440, "rew": -3.9365, "rew_std": 0.5545, "Agent": "PPO"}, {"env_step": 2396160, "rew": -4.6383, "rew_std": 0.2892, "Agent": "PPO"}, {"env_step": 2426880, "rew": -3.7809, "rew_std": 0.461, "Agent": "PPO"}, {"env_step": 2457600, "rew": -4.5572, "rew_std": 0.3636, "Agent": "PPO"}, {"env_step": 2488320, "rew": -5.2924, "rew_std": 0.3211, "Agent": "PPO"}, {"env_step": 2519040, "rew": -4.2562, "rew_std": 0.4444, "Agent": "PPO"}, {"env_step": 2549760, "rew": -4.0844, "rew_std": 0.4715, "Agent": "PPO"}, {"env_step": 2580480, "rew": -4.6425, "rew_std": 0.2153, "Agent": "PPO"}, {"env_step": 2611200, "rew": -4.1332, "rew_std": 0.5231, "Agent": "PPO"}, {"env_step": 2641920, "rew": -3.811, "rew_std": 0.4255, "Agent": "PPO"}, {"env_step": 2672640, "rew": -4.4177, "rew_std": 0.3892, "Agent": "PPO"}, {"env_step": 2703360, "rew": -3.9716, "rew_std": 0.5346, "Agent": "PPO"}, {"env_step": 2734080, "rew": -4.1433, "rew_std": 0.3098, "Agent": "PPO"}, {"env_step": 2764800, "rew": -4.4922, "rew_std": 0.4792, "Agent": "PPO"}, {"env_step": 2795520, "rew": -4.3185, "rew_std": 0.3626, "Agent": "PPO"}, {"env_step": 2826240, "rew": -4.077, "rew_std": 0.3572, "Agent": "PPO"}, {"env_step": 2856960, "rew": -4.9316, "rew_std": 0.4112, "Agent": "PPO"}, {"env_step": 2887680, "rew": -4.1553, "rew_std": 0.1359, "Agent": "PPO"}, {"env_step": 2918400, "rew": -4.3514, "rew_std": 0.2179, "Agent": "PPO"}, {"env_step": 2949120, "rew": -4.1512, "rew_std": 0.226, "Agent": "PPO"}, {"env_step": 2979840, "rew": -4.4676, "rew_std": 0.2695, "Agent": "PPO"}, {"env_step": 3010560, "rew": -4.1195, "rew_std": 0.2915, "Agent": "PPO"}, {"env_step": 3041280, "rew": -4.924, "rew_std": 0.4478, "Agent": "PPO"}, {"env_step": 3072000, "rew": -4.7199, "rew_std": 0.261, "Agent": "PPO"}, {"env_step": 0, "rew": -27.3232, "rew_std": 23.4601, "Agent": "TD3"}, {"env_step": 5000, "rew": -9.4278, "rew_std": 0.6088, "Agent": "TD3"}, {"env_step": 10000, "rew": -7.0669, "rew_std": 0.5544, "Agent": "TD3"}, {"env_step": 15000, "rew": -6.4267, "rew_std": 0.5535, "Agent": "TD3"}, {"env_step": 20000, "rew": -5.1856, "rew_std": 0.5122, "Agent": "TD3"}, {"env_step": 25000, "rew": -6.2298, "rew_std": 0.4873, "Agent": "TD3"}, {"env_step": 30000, "rew": -4.746, "rew_std": 0.2296, "Agent": "TD3"}, {"env_step": 35000, "rew": -4.9355, "rew_std": 0.4494, "Agent": "TD3"}, {"env_step": 40000, "rew": -5.18, "rew_std": 0.4861, "Agent": "TD3"}, {"env_step": 45000, "rew": -5.3703, "rew_std": 0.797, "Agent": "TD3"}, {"env_step": 50000, "rew": -5.2779, "rew_std": 0.5659, "Agent": "TD3"}, {"env_step": 55000, "rew": -5.2297, "rew_std": 0.3341, "Agent": "TD3"}, {"env_step": 60000, "rew": -4.5756, "rew_std": 0.476, "Agent": "TD3"}, {"env_step": 65000, "rew": -4.2738, "rew_std": 0.1586, "Agent": "TD3"}, {"env_step": 70000, "rew": -4.8618, "rew_std": 0.3402, "Agent": "TD3"}, {"env_step": 75000, "rew": -4.2569, "rew_std": 0.1832, "Agent": "TD3"}, {"env_step": 80000, "rew": -4.5128, "rew_std": 0.3919, "Agent": "TD3"}, {"env_step": 85000, "rew": -4.45, "rew_std": 0.1863, "Agent": "TD3"}, {"env_step": 90000, "rew": -5.1534, "rew_std": 0.3301, "Agent": "TD3"}, {"env_step": 95000, "rew": -4.618, "rew_std": 0.218, "Agent": "TD3"}, {"env_step": 100000, "rew": -4.6005, "rew_std": 0.2978, "Agent": "TD3"}, {"env_step": 105000, "rew": -4.7658, "rew_std": 0.3353, "Agent": "TD3"}, {"env_step": 110000, "rew": -4.8709, "rew_std": 0.4209, "Agent": "TD3"}, {"env_step": 115000, "rew": -3.8872, "rew_std": 0.1921, "Agent": "TD3"}, {"env_step": 120000, "rew": -3.5985, "rew_std": 0.2389, "Agent": "TD3"}, {"env_step": 125000, "rew": -3.8332, "rew_std": 0.2889, "Agent": "TD3"}, {"env_step": 130000, "rew": -4.3352, "rew_std": 0.2688, "Agent": "TD3"}, {"env_step": 135000, "rew": -4.2144, "rew_std": 0.5016, "Agent": "TD3"}, {"env_step": 140000, "rew": -4.4658, "rew_std": 0.3705, "Agent": "TD3"}, {"env_step": 145000, "rew": -4.9148, "rew_std": 0.1617, "Agent": "TD3"}, {"env_step": 150000, "rew": -4.37, "rew_std": 0.1933, "Agent": "TD3"}, {"env_step": 155000, "rew": -4.3036, "rew_std": 0.4578, "Agent": "TD3"}, {"env_step": 160000, "rew": -4.2312, "rew_std": 0.2589, "Agent": "TD3"}, {"env_step": 165000, "rew": -4.3598, "rew_std": 0.4077, "Agent": "TD3"}, {"env_step": 170000, "rew": -4.3913, "rew_std": 0.2397, "Agent": "TD3"}, {"env_step": 175000, "rew": -4.3605, "rew_std": 0.1915, "Agent": "TD3"}, {"env_step": 180000, "rew": -4.3441, "rew_std": 0.1972, "Agent": "TD3"}, {"env_step": 185000, "rew": -3.8606, "rew_std": 0.2643, "Agent": "TD3"}, {"env_step": 190000, "rew": -4.1763, "rew_std": 0.1379, "Agent": "TD3"}, {"env_step": 195000, "rew": -3.8127, "rew_std": 0.2737, "Agent": "TD3"}, {"env_step": 200000, "rew": -3.774, "rew_std": 0.3018, "Agent": "TD3"}, {"env_step": 205000, "rew": -4.2305, "rew_std": 0.301, "Agent": "TD3"}, {"env_step": 210000, "rew": -4.4027, "rew_std": 0.2059, "Agent": "TD3"}, {"env_step": 215000, "rew": -4.5156, "rew_std": 0.2303, "Agent": "TD3"}, {"env_step": 220000, "rew": -3.885, "rew_std": 0.3386, "Agent": "TD3"}, {"env_step": 225000, "rew": -4.3227, "rew_std": 0.2204, "Agent": "TD3"}, {"env_step": 230000, "rew": -4.3129, "rew_std": 0.2052, "Agent": "TD3"}, {"env_step": 235000, "rew": -3.4446, "rew_std": 0.2954, "Agent": "TD3"}, {"env_step": 240000, "rew": -4.47, "rew_std": 0.2525, "Agent": "TD3"}, {"env_step": 245000, "rew": -4.2606, "rew_std": 0.2477, "Agent": "TD3"}, {"env_step": 250000, "rew": -4.086, "rew_std": 0.4186, "Agent": "TD3"}, {"env_step": 255000, "rew": -3.5408, "rew_std": 0.273, "Agent": "TD3"}, {"env_step": 260000, "rew": -3.9576, "rew_std": 0.1268, "Agent": "TD3"}, {"env_step": 265000, "rew": -3.826, "rew_std": 0.2686, "Agent": "TD3"}, {"env_step": 270000, "rew": -3.9491, "rew_std": 0.2103, "Agent": "TD3"}, {"env_step": 275000, "rew": -3.9134, "rew_std": 0.2388, "Agent": "TD3"}, {"env_step": 280000, "rew": -3.9591, "rew_std": 0.2735, "Agent": "TD3"}, {"env_step": 285000, "rew": -4.3291, "rew_std": 0.1285, "Agent": "TD3"}, {"env_step": 290000, "rew": -3.6573, "rew_std": 0.1932, "Agent": "TD3"}, {"env_step": 295000, "rew": -3.7134, "rew_std": 0.135, "Agent": "TD3"}, {"env_step": 300000, "rew": -3.78, "rew_std": 0.3737, "Agent": "TD3"}, {"env_step": 305000, "rew": -3.8248, "rew_std": 0.1736, "Agent": "TD3"}, {"env_step": 310000, "rew": -4.18, "rew_std": 0.1973, "Agent": "TD3"}, {"env_step": 315000, "rew": -4.2059, "rew_std": 0.1313, "Agent": "TD3"}, {"env_step": 320000, "rew": -3.5267, "rew_std": 0.3696, "Agent": "TD3"}, {"env_step": 325000, "rew": -4.3458, "rew_std": 0.3499, "Agent": "TD3"}, {"env_step": 330000, "rew": -4.1234, "rew_std": 0.3483, "Agent": "TD3"}, {"env_step": 335000, "rew": -3.6075, "rew_std": 0.3162, "Agent": "TD3"}, {"env_step": 340000, "rew": -3.5364, "rew_std": 0.1874, "Agent": "TD3"}, {"env_step": 345000, "rew": -3.8618, "rew_std": 0.2639, "Agent": "TD3"}, {"env_step": 350000, "rew": -3.9008, "rew_std": 0.2792, "Agent": "TD3"}, {"env_step": 355000, "rew": -3.1281, "rew_std": 0.271, "Agent": "TD3"}, {"env_step": 360000, "rew": -3.6761, "rew_std": 0.2884, "Agent": "TD3"}, {"env_step": 365000, "rew": -4.5713, "rew_std": 0.1102, "Agent": "TD3"}, {"env_step": 370000, "rew": -3.6901, "rew_std": 0.3035, "Agent": "TD3"}, {"env_step": 375000, "rew": -4.0951, "rew_std": 0.2359, "Agent": "TD3"}, {"env_step": 380000, "rew": -4.1626, "rew_std": 0.1743, "Agent": "TD3"}, {"env_step": 385000, "rew": -3.9314, "rew_std": 0.3946, "Agent": "TD3"}, {"env_step": 390000, "rew": -4.7471, "rew_std": 0.2057, "Agent": "TD3"}, {"env_step": 395000, "rew": -3.9016, "rew_std": 0.4001, "Agent": "TD3"}, {"env_step": 400000, "rew": -3.7927, "rew_std": 0.1933, "Agent": "TD3"}, {"env_step": 405000, "rew": -4.1709, "rew_std": 0.2449, "Agent": "TD3"}, {"env_step": 410000, "rew": -4.0937, "rew_std": 0.2439, "Agent": "TD3"}, {"env_step": 415000, "rew": -3.8412, "rew_std": 0.187, "Agent": "TD3"}, {"env_step": 420000, "rew": -4.0207, "rew_std": 0.2532, "Agent": "TD3"}, {"env_step": 425000, "rew": -4.2583, "rew_std": 0.1668, "Agent": "TD3"}, {"env_step": 430000, "rew": -3.9042, "rew_std": 0.1975, "Agent": "TD3"}, {"env_step": 435000, "rew": -4.2115, "rew_std": 0.1991, "Agent": "TD3"}, {"env_step": 440000, "rew": -4.1096, "rew_std": 0.4061, "Agent": "TD3"}, {"env_step": 445000, "rew": -3.7729, "rew_std": 0.2087, "Agent": "TD3"}, {"env_step": 450000, "rew": -3.8751, "rew_std": 0.3315, "Agent": "TD3"}, {"env_step": 455000, "rew": -3.4159, "rew_std": 0.2461, "Agent": "TD3"}, {"env_step": 460000, "rew": -3.8447, "rew_std": 0.2259, "Agent": "TD3"}, {"env_step": 465000, "rew": -4.0669, "rew_std": 0.3227, "Agent": "TD3"}, {"env_step": 470000, "rew": -3.691, "rew_std": 0.2494, "Agent": "TD3"}, {"env_step": 475000, "rew": -3.3224, "rew_std": 0.3852, "Agent": "TD3"}, {"env_step": 480000, "rew": -4.0412, "rew_std": 0.2384, "Agent": "TD3"}, {"env_step": 485000, "rew": -4.0592, "rew_std": 0.3395, "Agent": "TD3"}, {"env_step": 490000, "rew": -3.2932, "rew_std": 0.2861, "Agent": "TD3"}, {"env_step": 495000, "rew": -3.9973, "rew_std": 0.1509, "Agent": "TD3"}, {"env_step": 500000, "rew": -3.8178, "rew_std": 0.2252, "Agent": "TD3"}, {"env_step": 505000, "rew": -4.2918, "rew_std": 0.3856, "Agent": "TD3"}, {"env_step": 510000, "rew": -3.8209, "rew_std": 0.2873, "Agent": "TD3"}, {"env_step": 515000, "rew": -3.9336, "rew_std": 0.2041, "Agent": "TD3"}, {"env_step": 520000, "rew": -4.0006, "rew_std": 0.215, "Agent": "TD3"}, {"env_step": 525000, "rew": -3.8263, "rew_std": 0.2583, "Agent": "TD3"}, {"env_step": 530000, "rew": -3.4156, "rew_std": 0.1398, "Agent": "TD3"}, {"env_step": 535000, "rew": -4.4681, "rew_std": 0.2342, "Agent": "TD3"}, {"env_step": 540000, "rew": -3.637, "rew_std": 0.1929, "Agent": "TD3"}, {"env_step": 545000, "rew": -3.5376, "rew_std": 0.2974, "Agent": "TD3"}, {"env_step": 550000, "rew": -4.2729, "rew_std": 0.4386, "Agent": "TD3"}, {"env_step": 555000, "rew": -3.9786, "rew_std": 0.2423, "Agent": "TD3"}, {"env_step": 560000, "rew": -3.4312, "rew_std": 0.1127, "Agent": "TD3"}, {"env_step": 565000, "rew": -4.3476, "rew_std": 0.3141, "Agent": "TD3"}, {"env_step": 570000, "rew": -3.4787, "rew_std": 0.1459, "Agent": "TD3"}, {"env_step": 575000, "rew": -4.0289, "rew_std": 0.2522, "Agent": "TD3"}, {"env_step": 580000, "rew": -3.3567, "rew_std": 0.2871, "Agent": "TD3"}, {"env_step": 585000, "rew": -3.2353, "rew_std": 0.2117, "Agent": "TD3"}, {"env_step": 590000, "rew": -3.362, "rew_std": 0.1691, "Agent": "TD3"}, {"env_step": 595000, "rew": -3.3161, "rew_std": 0.3261, "Agent": "TD3"}, {"env_step": 600000, "rew": -3.989, "rew_std": 0.2499, "Agent": "TD3"}, {"env_step": 605000, "rew": -3.9252, "rew_std": 0.1923, "Agent": "TD3"}, {"env_step": 610000, "rew": -4.7941, "rew_std": 0.3138, "Agent": "TD3"}, {"env_step": 615000, "rew": -4.0498, "rew_std": 0.2469, "Agent": "TD3"}, {"env_step": 620000, "rew": -4.5315, "rew_std": 0.0809, "Agent": "TD3"}, {"env_step": 625000, "rew": -3.6891, "rew_std": 0.4345, "Agent": "TD3"}, {"env_step": 630000, "rew": -3.6188, "rew_std": 0.4994, "Agent": "TD3"}, {"env_step": 635000, "rew": -3.5216, "rew_std": 0.1895, "Agent": "TD3"}, {"env_step": 640000, "rew": -3.6394, "rew_std": 0.2868, "Agent": "TD3"}, {"env_step": 645000, "rew": -3.8522, "rew_std": 0.2107, "Agent": "TD3"}, {"env_step": 650000, "rew": -3.1598, "rew_std": 0.3737, "Agent": "TD3"}, {"env_step": 655000, "rew": -3.939, "rew_std": 0.3151, "Agent": "TD3"}, {"env_step": 660000, "rew": -4.2649, "rew_std": 0.2185, "Agent": "TD3"}, {"env_step": 665000, "rew": -4.1026, "rew_std": 0.1811, "Agent": "TD3"}, {"env_step": 670000, "rew": -3.5874, "rew_std": 0.3452, "Agent": "TD3"}, {"env_step": 675000, "rew": -3.8099, "rew_std": 0.1105, "Agent": "TD3"}, {"env_step": 680000, "rew": -3.4478, "rew_std": 0.4465, "Agent": "TD3"}, {"env_step": 685000, "rew": -3.9152, "rew_std": 0.31, "Agent": "TD3"}, {"env_step": 690000, "rew": -3.2581, "rew_std": 0.181, "Agent": "TD3"}, {"env_step": 695000, "rew": -3.6871, "rew_std": 0.2137, "Agent": "TD3"}, {"env_step": 700000, "rew": -4.3676, "rew_std": 0.3509, "Agent": "TD3"}, {"env_step": 705000, "rew": -2.7017, "rew_std": 0.1631, "Agent": "TD3"}, {"env_step": 710000, "rew": -4.0376, "rew_std": 0.2119, "Agent": "TD3"}, {"env_step": 715000, "rew": -3.9039, "rew_std": 0.2119, "Agent": "TD3"}, {"env_step": 720000, "rew": -4.2988, "rew_std": 0.2461, "Agent": "TD3"}, {"env_step": 725000, "rew": -4.3014, "rew_std": 0.2111, "Agent": "TD3"}, {"env_step": 730000, "rew": -4.0589, "rew_std": 0.1674, "Agent": "TD3"}, {"env_step": 735000, "rew": -4.3312, "rew_std": 0.3965, "Agent": "TD3"}, {"env_step": 740000, "rew": -3.3715, "rew_std": 0.1813, "Agent": "TD3"}, {"env_step": 745000, "rew": -4.4481, "rew_std": 0.304, "Agent": "TD3"}, {"env_step": 750000, "rew": -3.7905, "rew_std": 0.3223, "Agent": "TD3"}, {"env_step": 755000, "rew": -3.9719, "rew_std": 0.2819, "Agent": "TD3"}, {"env_step": 760000, "rew": -4.2341, "rew_std": 0.1909, "Agent": "TD3"}, {"env_step": 765000, "rew": -3.9411, "rew_std": 0.348, "Agent": "TD3"}, {"env_step": 770000, "rew": -3.6554, "rew_std": 0.1726, "Agent": "TD3"}, {"env_step": 775000, "rew": -3.2103, "rew_std": 0.3632, "Agent": "TD3"}, {"env_step": 780000, "rew": -3.2774, "rew_std": 0.1973, "Agent": "TD3"}, {"env_step": 785000, "rew": -3.7977, "rew_std": 0.305, "Agent": "TD3"}, {"env_step": 790000, "rew": -3.7438, "rew_std": 0.1475, "Agent": "TD3"}, {"env_step": 795000, "rew": -4.2541, "rew_std": 0.2172, "Agent": "TD3"}, {"env_step": 800000, "rew": -4.1165, "rew_std": 0.1339, "Agent": "TD3"}, {"env_step": 805000, "rew": -3.9355, "rew_std": 0.1874, "Agent": "TD3"}, {"env_step": 810000, "rew": -4.0148, "rew_std": 0.1085, "Agent": "TD3"}, {"env_step": 815000, "rew": -3.6011, "rew_std": 0.2793, "Agent": "TD3"}, {"env_step": 820000, "rew": -4.1609, "rew_std": 0.1996, "Agent": "TD3"}, {"env_step": 825000, "rew": -3.8636, "rew_std": 0.2676, "Agent": "TD3"}, {"env_step": 830000, "rew": -3.9353, "rew_std": 0.3424, "Agent": "TD3"}, {"env_step": 835000, "rew": -3.9981, "rew_std": 0.195, "Agent": "TD3"}, {"env_step": 840000, "rew": -3.462, "rew_std": 0.2094, "Agent": "TD3"}, {"env_step": 845000, "rew": -3.9043, "rew_std": 0.2111, "Agent": "TD3"}, {"env_step": 850000, "rew": -3.8145, "rew_std": 0.344, "Agent": "TD3"}, {"env_step": 855000, "rew": -3.8187, "rew_std": 0.1498, "Agent": "TD3"}, {"env_step": 860000, "rew": -3.5996, "rew_std": 0.3091, "Agent": "TD3"}, {"env_step": 865000, "rew": -3.7927, "rew_std": 0.2665, "Agent": "TD3"}, {"env_step": 870000, "rew": -4.0968, "rew_std": 0.1984, "Agent": "TD3"}, {"env_step": 875000, "rew": -3.399, "rew_std": 0.16, "Agent": "TD3"}, {"env_step": 880000, "rew": -3.9339, "rew_std": 0.1483, "Agent": "TD3"}, {"env_step": 885000, "rew": -3.7215, "rew_std": 0.1435, "Agent": "TD3"}, {"env_step": 890000, "rew": -3.0608, "rew_std": 0.3411, "Agent": "TD3"}, {"env_step": 895000, "rew": -3.4966, "rew_std": 0.3495, "Agent": "TD3"}, {"env_step": 900000, "rew": -3.0725, "rew_std": 0.2359, "Agent": "TD3"}, {"env_step": 905000, "rew": -4.5566, "rew_std": 0.2284, "Agent": "TD3"}, {"env_step": 910000, "rew": -4.0288, "rew_std": 0.381, "Agent": "TD3"}, {"env_step": 915000, "rew": -3.9548, "rew_std": 0.2133, "Agent": "TD3"}, {"env_step": 920000, "rew": -4.0829, "rew_std": 0.3712, "Agent": "TD3"}, {"env_step": 925000, "rew": -3.356, "rew_std": 0.2326, "Agent": "TD3"}, {"env_step": 930000, "rew": -3.7336, "rew_std": 0.3556, "Agent": "TD3"}, {"env_step": 935000, "rew": -4.1592, "rew_std": 0.2811, "Agent": "TD3"}, {"env_step": 940000, "rew": -4.0395, "rew_std": 0.2811, "Agent": "TD3"}, {"env_step": 945000, "rew": -3.6727, "rew_std": 0.2061, "Agent": "TD3"}, {"env_step": 950000, "rew": -3.7449, "rew_std": 0.4064, "Agent": "TD3"}, {"env_step": 955000, "rew": -3.4838, "rew_std": 0.1478, "Agent": "TD3"}, {"env_step": 960000, "rew": -3.4326, "rew_std": 0.2707, "Agent": "TD3"}, {"env_step": 965000, "rew": -3.7454, "rew_std": 0.344, "Agent": "TD3"}, {"env_step": 970000, "rew": -4.2367, "rew_std": 0.2172, "Agent": "TD3"}, {"env_step": 975000, "rew": -4.144, "rew_std": 0.1141, "Agent": "TD3"}, {"env_step": 980000, "rew": -4.1952, "rew_std": 0.3218, "Agent": "TD3"}, {"env_step": 985000, "rew": -3.7304, "rew_std": 0.3967, "Agent": "TD3"}, {"env_step": 990000, "rew": -2.9973, "rew_std": 0.218, "Agent": "TD3"}, {"env_step": 995000, "rew": -3.234, "rew_std": 0.1885, "Agent": "TD3"}, {"env_step": 1000000, "rew": -3.8884, "rew_std": 0.272, "Agent": "TD3"}, {"env_step": 1005000, "rew": -4.1338, "rew_std": 0.2143, "Agent": "TD3"}, {"env_step": 1010000, "rew": -3.0098, "rew_std": 0.1208, "Agent": "TD3"}, {"env_step": 1015000, "rew": -4.1758, "rew_std": 0.3719, "Agent": "TD3"}, {"env_step": 1020000, "rew": -4.0399, "rew_std": 0.3482, "Agent": "TD3"}, {"env_step": 1025000, "rew": -4.2385, "rew_std": 0.2338, "Agent": "TD3"}, {"env_step": 1030000, "rew": -4.365, "rew_std": 0.2632, "Agent": "TD3"}, {"env_step": 1035000, "rew": -3.8108, "rew_std": 0.1679, "Agent": "TD3"}, {"env_step": 1040000, "rew": -4.28, "rew_std": 0.2992, "Agent": "TD3"}, {"env_step": 1045000, "rew": -3.7372, "rew_std": 0.2577, "Agent": "TD3"}, {"env_step": 1050000, "rew": -3.2307, "rew_std": 0.2714, "Agent": "TD3"}, {"env_step": 1055000, "rew": -3.9885, "rew_std": 0.4439, "Agent": "TD3"}, {"env_step": 1060000, "rew": -3.7267, "rew_std": 0.2736, "Agent": "TD3"}, {"env_step": 1065000, "rew": -4.1032, "rew_std": 0.2142, "Agent": "TD3"}, {"env_step": 1070000, "rew": -3.7962, "rew_std": 0.1767, "Agent": "TD3"}, {"env_step": 1075000, "rew": -2.8543, "rew_std": 0.3636, "Agent": "TD3"}, {"env_step": 1080000, "rew": -3.6066, "rew_std": 0.0793, "Agent": "TD3"}, {"env_step": 1085000, "rew": -3.9929, "rew_std": 0.1699, "Agent": "TD3"}, {"env_step": 1090000, "rew": -3.2463, "rew_std": 0.3051, "Agent": "TD3"}, {"env_step": 1095000, "rew": -3.5581, "rew_std": 0.2546, "Agent": "TD3"}, {"env_step": 1100000, "rew": -4.5702, "rew_std": 0.3293, "Agent": "TD3"}, {"env_step": 1105000, "rew": -3.4873, "rew_std": 0.1964, "Agent": "TD3"}, {"env_step": 1110000, "rew": -4.4129, "rew_std": 0.2345, "Agent": "TD3"}, {"env_step": 1115000, "rew": -4.0473, "rew_std": 0.2341, "Agent": "TD3"}, {"env_step": 1120000, "rew": -4.1743, "rew_std": 0.4852, "Agent": "TD3"}, {"env_step": 1125000, "rew": -3.6916, "rew_std": 0.2553, "Agent": "TD3"}, {"env_step": 1130000, "rew": -4.2822, "rew_std": 0.3409, "Agent": "TD3"}, {"env_step": 1135000, "rew": -3.4592, "rew_std": 0.1341, "Agent": "TD3"}, {"env_step": 1140000, "rew": -3.7917, "rew_std": 0.2305, "Agent": "TD3"}, {"env_step": 1145000, "rew": -3.6923, "rew_std": 0.1766, "Agent": "TD3"}, {"env_step": 1150000, "rew": -3.6304, "rew_std": 0.2707, "Agent": "TD3"}, {"env_step": 1155000, "rew": -4.0343, "rew_std": 0.179, "Agent": "TD3"}, {"env_step": 1160000, "rew": -3.2482, "rew_std": 0.2482, "Agent": "TD3"}, {"env_step": 1165000, "rew": -4.4312, "rew_std": 0.4369, "Agent": "TD3"}, {"env_step": 1170000, "rew": -4.6023, "rew_std": 0.5582, "Agent": "TD3"}, {"env_step": 1175000, "rew": -2.9858, "rew_std": 0.2303, "Agent": "TD3"}, {"env_step": 1180000, "rew": -3.4268, "rew_std": 0.1277, "Agent": "TD3"}, {"env_step": 1185000, "rew": -3.8793, "rew_std": 0.3748, "Agent": "TD3"}, {"env_step": 1190000, "rew": -4.358, "rew_std": 0.2256, "Agent": "TD3"}, {"env_step": 1195000, "rew": -3.9155, "rew_std": 0.1785, "Agent": "TD3"}, {"env_step": 1200000, "rew": -3.9947, "rew_std": 0.4121, "Agent": "TD3"}, {"env_step": 1205000, "rew": -3.6627, "rew_std": 0.1623, "Agent": "TD3"}, {"env_step": 1210000, "rew": -3.765, "rew_std": 0.4052, "Agent": "TD3"}, {"env_step": 1215000, "rew": -3.5107, "rew_std": 0.3295, "Agent": "TD3"}, {"env_step": 1220000, "rew": -4.0312, "rew_std": 0.2906, "Agent": "TD3"}, {"env_step": 1225000, "rew": -3.3748, "rew_std": 0.1568, "Agent": "TD3"}, {"env_step": 1230000, "rew": -3.8248, "rew_std": 0.1543, "Agent": "TD3"}, {"env_step": 1235000, "rew": -4.1974, "rew_std": 0.1718, "Agent": "TD3"}, {"env_step": 1240000, "rew": -3.4136, "rew_std": 0.2672, "Agent": "TD3"}, {"env_step": 1245000, "rew": -4.0437, "rew_std": 0.1481, "Agent": "TD3"}, {"env_step": 1250000, "rew": -4.1661, "rew_std": 0.2663, "Agent": "TD3"}, {"env_step": 0, "rew": -31.7242, "rew_std": 1.1515, "Agent": "REINFORCE"}, {"env_step": 30720, "rew": -32.8475, "rew_std": 0.7602, "Agent": "REINFORCE"}, {"env_step": 61440, "rew": -31.4946, "rew_std": 0.9164, "Agent": "REINFORCE"}, {"env_step": 92160, "rew": -31.7964, "rew_std": 0.8369, "Agent": "REINFORCE"}, {"env_step": 122880, "rew": -31.0148, "rew_std": 0.9304, "Agent": "REINFORCE"}, {"env_step": 153600, "rew": -30.2386, "rew_std": 0.9128, "Agent": "REINFORCE"}, {"env_step": 184320, "rew": -30.2757, "rew_std": 0.867, "Agent": "REINFORCE"}, {"env_step": 215040, "rew": -30.1909, "rew_std": 1.1399, "Agent": "REINFORCE"}, {"env_step": 245760, "rew": -29.6005, "rew_std": 1.1925, "Agent": "REINFORCE"}, {"env_step": 276480, "rew": -29.2278, "rew_std": 0.861, "Agent": "REINFORCE"}, {"env_step": 307200, "rew": -27.9807, "rew_std": 0.6982, "Agent": "REINFORCE"}, {"env_step": 337920, "rew": -28.2742, "rew_std": 0.692, "Agent": "REINFORCE"}, {"env_step": 368640, "rew": -29.0547, "rew_std": 1.4016, "Agent": "REINFORCE"}, {"env_step": 399360, "rew": -27.0411, "rew_std": 1.2675, "Agent": "REINFORCE"}, {"env_step": 430080, "rew": -27.1825, "rew_std": 0.5854, "Agent": "REINFORCE"}, {"env_step": 460800, "rew": -27.4172, "rew_std": 1.2445, "Agent": "REINFORCE"}, {"env_step": 491520, "rew": -26.1982, "rew_std": 0.8664, "Agent": "REINFORCE"}, {"env_step": 522240, "rew": -26.4559, "rew_std": 1.0527, "Agent": "REINFORCE"}, {"env_step": 552960, "rew": -26.471, "rew_std": 0.7768, "Agent": "REINFORCE"}, {"env_step": 583680, "rew": -25.7617, "rew_std": 1.0321, "Agent": "REINFORCE"}, {"env_step": 614400, "rew": -26.0457, "rew_std": 0.7244, "Agent": "REINFORCE"}, {"env_step": 645120, "rew": -25.0898, "rew_std": 1.1499, "Agent": "REINFORCE"}, {"env_step": 675840, "rew": -25.8386, "rew_std": 0.9712, "Agent": "REINFORCE"}, {"env_step": 706560, "rew": -24.9295, "rew_std": 1.1758, "Agent": "REINFORCE"}, {"env_step": 737280, "rew": -23.7776, "rew_std": 0.8549, "Agent": "REINFORCE"}, {"env_step": 768000, "rew": -24.0209, "rew_std": 0.968, "Agent": "REINFORCE"}, {"env_step": 798720, "rew": -23.2574, "rew_std": 1.0228, "Agent": "REINFORCE"}, {"env_step": 829440, "rew": -23.4654, "rew_std": 1.1348, "Agent": "REINFORCE"}, {"env_step": 860160, "rew": -23.1139, "rew_std": 1.1578, "Agent": "REINFORCE"}, {"env_step": 890880, "rew": -21.8823, "rew_std": 1.0453, "Agent": "REINFORCE"}, {"env_step": 921600, "rew": -21.9515, "rew_std": 0.8806, "Agent": "REINFORCE"}, {"env_step": 952320, "rew": -21.6887, "rew_std": 1.4182, "Agent": "REINFORCE"}, {"env_step": 983040, "rew": -21.4815, "rew_std": 0.7857, "Agent": "REINFORCE"}, {"env_step": 1013760, "rew": -20.9373, "rew_std": 1.0882, "Agent": "REINFORCE"}, {"env_step": 1044480, "rew": -21.2495, "rew_std": 1.0276, "Agent": "REINFORCE"}, {"env_step": 1075200, "rew": -20.0153, "rew_std": 0.7888, "Agent": "REINFORCE"}, {"env_step": 1105920, "rew": -20.4975, "rew_std": 1.0074, "Agent": "REINFORCE"}, {"env_step": 1136640, "rew": -20.146, "rew_std": 1.0807, "Agent": "REINFORCE"}, {"env_step": 1167360, "rew": -19.7466, "rew_std": 0.796, "Agent": "REINFORCE"}, {"env_step": 1198080, "rew": -18.9596, "rew_std": 0.9519, "Agent": "REINFORCE"}, {"env_step": 1228800, "rew": -20.5227, "rew_std": 1.0082, "Agent": "REINFORCE"}, {"env_step": 1259520, "rew": -18.945, "rew_std": 1.1814, "Agent": "REINFORCE"}, {"env_step": 1290240, "rew": -18.4987, "rew_std": 0.6713, "Agent": "REINFORCE"}, {"env_step": 1320960, "rew": -19.6578, "rew_std": 0.9521, "Agent": "REINFORCE"}, {"env_step": 1351680, "rew": -17.8018, "rew_std": 0.8241, "Agent": "REINFORCE"}, {"env_step": 1382400, "rew": -17.8281, "rew_std": 0.8157, "Agent": "REINFORCE"}, {"env_step": 1413120, "rew": -17.0201, "rew_std": 1.0223, "Agent": "REINFORCE"}, {"env_step": 1443840, "rew": -16.9074, "rew_std": 1.4043, "Agent": "REINFORCE"}, {"env_step": 1474560, "rew": -17.6015, "rew_std": 1.4143, "Agent": "REINFORCE"}, {"env_step": 1505280, "rew": -16.7421, "rew_std": 0.9056, "Agent": "REINFORCE"}, {"env_step": 1536000, "rew": -16.1835, "rew_std": 0.9015, "Agent": "REINFORCE"}, {"env_step": 1566720, "rew": -17.2971, "rew_std": 1.0613, "Agent": "REINFORCE"}, {"env_step": 1597440, "rew": -15.9043, "rew_std": 0.9545, "Agent": "REINFORCE"}, {"env_step": 1628160, "rew": -16.0512, "rew_std": 1.1131, "Agent": "REINFORCE"}, {"env_step": 1658880, "rew": -15.4652, "rew_std": 0.9131, "Agent": "REINFORCE"}, {"env_step": 1689600, "rew": -15.246, "rew_std": 1.0308, "Agent": "REINFORCE"}, {"env_step": 1720320, "rew": -14.9502, "rew_std": 1.1819, "Agent": "REINFORCE"}, {"env_step": 1751040, "rew": -15.1105, "rew_std": 0.8577, "Agent": "REINFORCE"}, {"env_step": 1781760, "rew": -14.5965, "rew_std": 0.9296, "Agent": "REINFORCE"}, {"env_step": 1812480, "rew": -14.8261, "rew_std": 0.8252, "Agent": "REINFORCE"}, {"env_step": 1843200, "rew": -14.1788, "rew_std": 0.5964, "Agent": "REINFORCE"}, {"env_step": 1873920, "rew": -14.5974, "rew_std": 0.9389, "Agent": "REINFORCE"}, {"env_step": 1904640, "rew": -13.6165, "rew_std": 1.0934, "Agent": "REINFORCE"}, {"env_step": 1935360, "rew": -13.5211, "rew_std": 0.8089, "Agent": "REINFORCE"}, {"env_step": 1966080, "rew": -14.1801, "rew_std": 0.6711, "Agent": "REINFORCE"}, {"env_step": 1996800, "rew": -13.1272, "rew_std": 0.7476, "Agent": "REINFORCE"}, {"env_step": 2027520, "rew": -13.2716, "rew_std": 0.8896, "Agent": "REINFORCE"}, {"env_step": 2058240, "rew": -14.2973, "rew_std": 0.7262, "Agent": "REINFORCE"}, {"env_step": 2088960, "rew": -13.4797, "rew_std": 0.9319, "Agent": "REINFORCE"}, {"env_step": 2119680, "rew": -13.3317, "rew_std": 0.7338, "Agent": "REINFORCE"}, {"env_step": 2150400, "rew": -13.731, "rew_std": 0.6122, "Agent": "REINFORCE"}, {"env_step": 2181120, "rew": -13.9919, "rew_std": 0.7474, "Agent": "REINFORCE"}, {"env_step": 2211840, "rew": -12.7447, "rew_std": 0.6264, "Agent": "REINFORCE"}, {"env_step": 2242560, "rew": -13.8354, "rew_std": 0.7329, "Agent": "REINFORCE"}, {"env_step": 2273280, "rew": -12.781, "rew_std": 0.5716, "Agent": "REINFORCE"}, {"env_step": 2304000, "rew": -13.3988, "rew_std": 0.5085, "Agent": "REINFORCE"}, {"env_step": 2334720, "rew": -12.2226, "rew_std": 0.5718, "Agent": "REINFORCE"}, {"env_step": 2365440, "rew": -11.5359, "rew_std": 0.6257, "Agent": "REINFORCE"}, {"env_step": 2396160, "rew": -12.9682, "rew_std": 0.6416, "Agent": "REINFORCE"}, {"env_step": 2426880, "rew": -11.5897, "rew_std": 0.8087, "Agent": "REINFORCE"}, {"env_step": 2457600, "rew": -12.1057, "rew_std": 0.9083, "Agent": "REINFORCE"}, {"env_step": 2488320, "rew": -13.4054, "rew_std": 0.5202, "Agent": "REINFORCE"}, {"env_step": 2519040, "rew": -11.6246, "rew_std": 1.0265, "Agent": "REINFORCE"}, {"env_step": 2549760, "rew": -11.6709, "rew_std": 0.6445, "Agent": "REINFORCE"}, {"env_step": 2580480, "rew": -11.9136, "rew_std": 0.8746, "Agent": "REINFORCE"}, {"env_step": 2611200, "rew": -11.4543, "rew_std": 0.5406, "Agent": "REINFORCE"}, {"env_step": 2641920, "rew": -10.8488, "rew_std": 0.7072, "Agent": "REINFORCE"}, {"env_step": 2672640, "rew": -11.9148, "rew_std": 0.6987, "Agent": "REINFORCE"}, {"env_step": 2703360, "rew": -10.8701, "rew_std": 0.6498, "Agent": "REINFORCE"}, {"env_step": 2734080, "rew": -11.1025, "rew_std": 0.7378, "Agent": "REINFORCE"}, {"env_step": 2764800, "rew": -11.403, "rew_std": 0.7242, "Agent": "REINFORCE"}, {"env_step": 2795520, "rew": -11.4606, "rew_std": 1.0069, "Agent": "REINFORCE"}, {"env_step": 2826240, "rew": -10.8376, "rew_std": 0.3489, "Agent": "REINFORCE"}, {"env_step": 2856960, "rew": -12.1351, "rew_std": 0.6699, "Agent": "REINFORCE"}, {"env_step": 2887680, "rew": -10.9223, "rew_std": 0.5095, "Agent": "REINFORCE"}, {"env_step": 2918400, "rew": -11.001, "rew_std": 0.4022, "Agent": "REINFORCE"}, {"env_step": 2949120, "rew": -10.5209, "rew_std": 0.662, "Agent": "REINFORCE"}, {"env_step": 2979840, "rew": -11.2583, "rew_std": 0.6426, "Agent": "REINFORCE"}, {"env_step": 3010560, "rew": -10.5418, "rew_std": 0.5359, "Agent": "REINFORCE"}, {"env_step": 3041280, "rew": -11.3974, "rew_std": 0.4321, "Agent": "REINFORCE"}, {"env_step": 3072000, "rew": -11.3566, "rew_std": 0.4394, "Agent": "REINFORCE"}, {"env_step": 3102720, "rew": -11.0647, "rew_std": 0.6376, "Agent": "REINFORCE"}, {"env_step": 3133440, "rew": -10.267, "rew_std": 0.5248, "Agent": "REINFORCE"}, {"env_step": 3164160, "rew": -9.4678, "rew_std": 0.6162, "Agent": "REINFORCE"}, {"env_step": 3194880, "rew": -10.6999, "rew_std": 0.5867, "Agent": "REINFORCE"}, {"env_step": 3225600, "rew": -10.2684, "rew_std": 0.8921, "Agent": "REINFORCE"}, {"env_step": 3256320, "rew": -10.4667, "rew_std": 0.734, "Agent": "REINFORCE"}, {"env_step": 3287040, "rew": -10.2591, "rew_std": 0.6946, "Agent": "REINFORCE"}, {"env_step": 3317760, "rew": -10.0482, "rew_std": 0.614, "Agent": "REINFORCE"}, {"env_step": 3348480, "rew": -10.5616, "rew_std": 0.7932, "Agent": "REINFORCE"}, {"env_step": 3379200, "rew": -9.3124, "rew_std": 0.4568, "Agent": "REINFORCE"}, {"env_step": 3409920, "rew": -10.3009, "rew_std": 0.7108, "Agent": "REINFORCE"}, {"env_step": 3440640, "rew": -10.01, "rew_std": 0.4446, "Agent": "REINFORCE"}, {"env_step": 3471360, "rew": -10.0028, "rew_std": 0.7494, "Agent": "REINFORCE"}, {"env_step": 3502080, "rew": -9.7224, "rew_std": 0.3233, "Agent": "REINFORCE"}, {"env_step": 3532800, "rew": -9.9523, "rew_std": 0.4799, "Agent": "REINFORCE"}, {"env_step": 3563520, "rew": -9.4691, "rew_std": 0.3737, "Agent": "REINFORCE"}, {"env_step": 3594240, "rew": -9.7658, "rew_std": 0.3515, "Agent": "REINFORCE"}, {"env_step": 3624960, "rew": -10.0672, "rew_std": 1.0384, "Agent": "REINFORCE"}, {"env_step": 3655680, "rew": -9.4751, "rew_std": 0.6451, "Agent": "REINFORCE"}, {"env_step": 3686400, "rew": -10.7983, "rew_std": 0.5735, "Agent": "REINFORCE"}, {"env_step": 3717120, "rew": -9.8788, "rew_std": 0.5075, "Agent": "REINFORCE"}, {"env_step": 3747840, "rew": -10.0776, "rew_std": 0.455, "Agent": "REINFORCE"}, {"env_step": 3778560, "rew": -9.0511, "rew_std": 0.5551, "Agent": "REINFORCE"}, {"env_step": 3809280, "rew": -10.5304, "rew_std": 0.5492, "Agent": "REINFORCE"}, {"env_step": 3840000, "rew": -10.1546, "rew_std": 1.0191, "Agent": "REINFORCE"}, {"env_step": 3870720, "rew": -9.3241, "rew_std": 1.0923, "Agent": "REINFORCE"}, {"env_step": 3901440, "rew": -8.9206, "rew_std": 0.5791, "Agent": "REINFORCE"}, {"env_step": 3932160, "rew": -9.6375, "rew_std": 0.5193, "Agent": "REINFORCE"}, {"env_step": 3962880, "rew": -9.843, "rew_std": 0.6557, "Agent": "REINFORCE"}, {"env_step": 3993600, "rew": -9.2655, "rew_std": 0.5223, "Agent": "REINFORCE"}, {"env_step": 4024320, "rew": -9.0418, "rew_std": 0.9985, "Agent": "REINFORCE"}, {"env_step": 4055040, "rew": -8.9568, "rew_std": 0.633, "Agent": "REINFORCE"}, {"env_step": 4085760, "rew": -8.8228, "rew_std": 0.5866, "Agent": "REINFORCE"}, {"env_step": 4116480, "rew": -9.051, "rew_std": 0.4739, "Agent": "REINFORCE"}, {"env_step": 4147200, "rew": -9.2519, "rew_std": 0.7584, "Agent": "REINFORCE"}, {"env_step": 4177920, "rew": -9.1386, "rew_std": 0.4962, "Agent": "REINFORCE"}, {"env_step": 4208640, "rew": -9.568, "rew_std": 0.4807, "Agent": "REINFORCE"}, {"env_step": 4239360, "rew": -9.235, "rew_std": 0.6097, "Agent": "REINFORCE"}, {"env_step": 4270080, "rew": -9.2398, "rew_std": 0.9416, "Agent": "REINFORCE"}, {"env_step": 4300800, "rew": -8.7664, "rew_std": 0.5432, "Agent": "REINFORCE"}, {"env_step": 4331520, "rew": -8.7303, "rew_std": 0.6987, "Agent": "REINFORCE"}, {"env_step": 4362240, "rew": -8.3891, "rew_std": 0.5771, "Agent": "REINFORCE"}, {"env_step": 4392960, "rew": -7.6193, "rew_std": 0.6167, "Agent": "REINFORCE"}, {"env_step": 4423680, "rew": -8.6555, "rew_std": 0.5337, "Agent": "REINFORCE"}, {"env_step": 4454400, "rew": -7.9336, "rew_std": 0.4842, "Agent": "REINFORCE"}, {"env_step": 4485120, "rew": -8.0155, "rew_std": 0.5302, "Agent": "REINFORCE"}, {"env_step": 4515840, "rew": -8.5184, "rew_std": 0.3602, "Agent": "REINFORCE"}, {"env_step": 4546560, "rew": -9.7916, "rew_std": 0.4676, "Agent": "REINFORCE"}, {"env_step": 4577280, "rew": -9.0749, "rew_std": 1.0043, "Agent": "REINFORCE"}, {"env_step": 4608000, "rew": -9.0557, "rew_std": 0.4831, "Agent": "REINFORCE"}, {"env_step": 4638720, "rew": -8.2344, "rew_std": 0.4451, "Agent": "REINFORCE"}, {"env_step": 4669440, "rew": -8.4418, "rew_std": 0.5803, "Agent": "REINFORCE"}, {"env_step": 4700160, "rew": -8.3141, "rew_std": 0.398, "Agent": "REINFORCE"}, {"env_step": 4730880, "rew": -8.2198, "rew_std": 0.3204, "Agent": "REINFORCE"}, {"env_step": 4761600, "rew": -9.6126, "rew_std": 0.7645, "Agent": "REINFORCE"}, {"env_step": 4792320, "rew": -8.9173, "rew_std": 0.4035, "Agent": "REINFORCE"}, {"env_step": 4823040, "rew": -7.9342, "rew_std": 0.5715, "Agent": "REINFORCE"}, {"env_step": 4853760, "rew": -8.633, "rew_std": 0.7986, "Agent": "REINFORCE"}, {"env_step": 4884480, "rew": -8.5991, "rew_std": 0.4252, "Agent": "REINFORCE"}, {"env_step": 4915200, "rew": -8.3731, "rew_std": 0.5851, "Agent": "REINFORCE"}, {"env_step": 4945920, "rew": -8.472, "rew_std": 0.6437, "Agent": "REINFORCE"}, {"env_step": 4976640, "rew": -9.0202, "rew_std": 0.568, "Agent": "REINFORCE"}, {"env_step": 5007360, "rew": -7.6257, "rew_std": 0.4051, "Agent": "REINFORCE"}, {"env_step": 5038080, "rew": -7.5025, "rew_std": 0.4499, "Agent": "REINFORCE"}, {"env_step": 5068800, "rew": -7.5077, "rew_std": 0.5008, "Agent": "REINFORCE"}, {"env_step": 5099520, "rew": -8.1766, "rew_std": 0.6425, "Agent": "REINFORCE"}, {"env_step": 5130240, "rew": -7.6867, "rew_std": 0.3841, "Agent": "REINFORCE"}, {"env_step": 5160960, "rew": -7.8887, "rew_std": 0.5593, "Agent": "REINFORCE"}, {"env_step": 5191680, "rew": -7.2022, "rew_std": 0.5648, "Agent": "REINFORCE"}, {"env_step": 5222400, "rew": -8.1184, "rew_std": 0.593, "Agent": "REINFORCE"}, {"env_step": 5253120, "rew": -8.1738, "rew_std": 0.4971, "Agent": "REINFORCE"}, {"env_step": 5283840, "rew": -7.6917, "rew_std": 0.6011, "Agent": "REINFORCE"}, {"env_step": 5314560, "rew": -8.0604, "rew_std": 0.6677, "Agent": "REINFORCE"}, {"env_step": 5345280, "rew": -8.5485, "rew_std": 0.5998, "Agent": "REINFORCE"}, {"env_step": 5376000, "rew": -7.9608, "rew_std": 0.8164, "Agent": "REINFORCE"}, {"env_step": 5406720, "rew": -7.1804, "rew_std": 0.4197, "Agent": "REINFORCE"}, {"env_step": 5437440, "rew": -7.7564, "rew_std": 0.5879, "Agent": "REINFORCE"}, {"env_step": 5468160, "rew": -7.7709, "rew_std": 0.4791, "Agent": "REINFORCE"}, {"env_step": 5498880, "rew": -8.6862, "rew_std": 0.6034, "Agent": "REINFORCE"}, {"env_step": 5529600, "rew": -7.3637, "rew_std": 0.4003, "Agent": "REINFORCE"}, {"env_step": 5560320, "rew": -8.2041, "rew_std": 0.6825, "Agent": "REINFORCE"}, {"env_step": 5591040, "rew": -7.5837, "rew_std": 1.07, "Agent": "REINFORCE"}, {"env_step": 5621760, "rew": -8.0955, "rew_std": 0.5087, "Agent": "REINFORCE"}, {"env_step": 5652480, "rew": -7.9267, "rew_std": 0.3496, "Agent": "REINFORCE"}, {"env_step": 5683200, "rew": -8.4919, "rew_std": 0.5083, "Agent": "REINFORCE"}, {"env_step": 5713920, "rew": -7.7982, "rew_std": 0.6942, "Agent": "REINFORCE"}, {"env_step": 5744640, "rew": -7.5888, "rew_std": 0.814, "Agent": "REINFORCE"}, {"env_step": 5775360, "rew": -7.7097, "rew_std": 0.9339, "Agent": "REINFORCE"}, {"env_step": 5806080, "rew": -8.5273, "rew_std": 0.5199, "Agent": "REINFORCE"}, {"env_step": 5836800, "rew": -7.8432, "rew_std": 0.3993, "Agent": "REINFORCE"}, {"env_step": 5867520, "rew": -6.9768, "rew_std": 0.3155, "Agent": "REINFORCE"}, {"env_step": 5898240, "rew": -8.3769, "rew_std": 0.4494, "Agent": "REINFORCE"}, {"env_step": 5928960, "rew": -7.5693, "rew_std": 0.4086, "Agent": "REINFORCE"}, {"env_step": 5959680, "rew": -7.9647, "rew_std": 0.3701, "Agent": "REINFORCE"}, {"env_step": 5990400, "rew": -8.3405, "rew_std": 0.636, "Agent": "REINFORCE"}, {"env_step": 6021120, "rew": -6.4293, "rew_std": 0.3667, "Agent": "REINFORCE"}, {"env_step": 6051840, "rew": -7.4603, "rew_std": 0.5929, "Agent": "REINFORCE"}, {"env_step": 6082560, "rew": -7.6826, "rew_std": 0.2479, "Agent": "REINFORCE"}, {"env_step": 6113280, "rew": -7.3964, "rew_std": 0.3839, "Agent": "REINFORCE"}, {"env_step": 6144000, "rew": -7.2288, "rew_std": 0.4363, "Agent": "REINFORCE"}, {"env_step": 6174720, "rew": -7.1334, "rew_std": 0.2158, "Agent": "REINFORCE"}, {"env_step": 6205440, "rew": -7.5344, "rew_std": 0.846, "Agent": "REINFORCE"}, {"env_step": 6236160, "rew": -6.912, "rew_std": 0.4014, "Agent": "REINFORCE"}, {"env_step": 6266880, "rew": -7.9701, "rew_std": 0.5672, "Agent": "REINFORCE"}, {"env_step": 6297600, "rew": -7.8618, "rew_std": 0.5215, "Agent": "REINFORCE"}, {"env_step": 6328320, "rew": -8.1969, "rew_std": 0.5516, "Agent": "REINFORCE"}, {"env_step": 6359040, "rew": -8.1615, "rew_std": 0.5294, "Agent": "REINFORCE"}, {"env_step": 6389760, "rew": -7.4611, "rew_std": 0.2738, "Agent": "REINFORCE"}, {"env_step": 6420480, "rew": -7.658, "rew_std": 0.487, "Agent": "REINFORCE"}, {"env_step": 6451200, "rew": -7.0698, "rew_std": 0.3777, "Agent": "REINFORCE"}, {"env_step": 6481920, "rew": -8.3339, "rew_std": 0.3772, "Agent": "REINFORCE"}, {"env_step": 6512640, "rew": -7.4882, "rew_std": 0.7056, "Agent": "REINFORCE"}, {"env_step": 6543360, "rew": -6.911, "rew_std": 0.6282, "Agent": "REINFORCE"}, {"env_step": 6574080, "rew": -7.9438, "rew_std": 0.7116, "Agent": "REINFORCE"}, {"env_step": 6604800, "rew": -7.4463, "rew_std": 0.4285, "Agent": "REINFORCE"}, {"env_step": 6635520, "rew": -7.0292, "rew_std": 0.4409, "Agent": "REINFORCE"}, {"env_step": 6666240, "rew": -7.2936, "rew_std": 0.4047, "Agent": "REINFORCE"}, {"env_step": 6696960, "rew": -7.2766, "rew_std": 0.4944, "Agent": "REINFORCE"}, {"env_step": 6727680, "rew": -7.4212, "rew_std": 0.6075, "Agent": "REINFORCE"}, {"env_step": 6758400, "rew": -6.9896, "rew_std": 0.6367, "Agent": "REINFORCE"}, {"env_step": 6789120, "rew": -6.7185, "rew_std": 0.4203, "Agent": "REINFORCE"}, {"env_step": 6819840, "rew": -7.0371, "rew_std": 0.4686, "Agent": "REINFORCE"}, {"env_step": 6850560, "rew": -7.61, "rew_std": 0.7566, "Agent": "REINFORCE"}, {"env_step": 6881280, "rew": -7.5168, "rew_std": 0.2887, "Agent": "REINFORCE"}, {"env_step": 6912000, "rew": -7.4282, "rew_std": 0.3962, "Agent": "REINFORCE"}, {"env_step": 6942720, "rew": -6.5424, "rew_std": 0.2874, "Agent": "REINFORCE"}, {"env_step": 6973440, "rew": -8.4729, "rew_std": 0.3012, "Agent": "REINFORCE"}, {"env_step": 7004160, "rew": -7.9614, "rew_std": 0.5518, "Agent": "REINFORCE"}, {"env_step": 7034880, "rew": -6.014, "rew_std": 0.3795, "Agent": "REINFORCE"}, {"env_step": 7065600, "rew": -6.993, "rew_std": 0.3695, "Agent": "REINFORCE"}, {"env_step": 7096320, "rew": -7.1158, "rew_std": 0.6192, "Agent": "REINFORCE"}, {"env_step": 7127040, "rew": -7.4814, "rew_std": 0.929, "Agent": "REINFORCE"}, {"env_step": 7157760, "rew": -6.9696, "rew_std": 0.4179, "Agent": "REINFORCE"}, {"env_step": 7188480, "rew": -7.0346, "rew_std": 0.5461, "Agent": "REINFORCE"}, {"env_step": 7219200, "rew": -7.3778, "rew_std": 0.4065, "Agent": "REINFORCE"}, {"env_step": 7249920, "rew": -7.3903, "rew_std": 0.4957, "Agent": "REINFORCE"}, {"env_step": 7280640, "rew": -6.8337, "rew_std": 0.4496, "Agent": "REINFORCE"}, {"env_step": 7311360, "rew": -6.3841, "rew_std": 0.3943, "Agent": "REINFORCE"}, {"env_step": 7342080, "rew": -6.7424, "rew_std": 0.5448, "Agent": "REINFORCE"}, {"env_step": 7372800, "rew": -7.0104, "rew_std": 0.4565, "Agent": "REINFORCE"}, {"env_step": 7403520, "rew": -7.002, "rew_std": 0.7382, "Agent": "REINFORCE"}, {"env_step": 7434240, "rew": -6.6108, "rew_std": 0.4492, "Agent": "REINFORCE"}, {"env_step": 7464960, "rew": -6.5709, "rew_std": 0.6859, "Agent": "REINFORCE"}, {"env_step": 7495680, "rew": -7.881, "rew_std": 0.6181, "Agent": "REINFORCE"}, {"env_step": 7526400, "rew": -7.4604, "rew_std": 0.6759, "Agent": "REINFORCE"}, {"env_step": 7557120, "rew": -6.7943, "rew_std": 0.2675, "Agent": "REINFORCE"}, {"env_step": 7587840, "rew": -6.628, "rew_std": 0.2949, "Agent": "REINFORCE"}, {"env_step": 7618560, "rew": -7.1264, "rew_std": 0.2886, "Agent": "REINFORCE"}, {"env_step": 7649280, "rew": -7.0895, "rew_std": 0.2166, "Agent": "REINFORCE"}, {"env_step": 7680000, "rew": -7.2885, "rew_std": 0.4005, "Agent": "REINFORCE"}, {"env_step": 7710720, "rew": -7.4407, "rew_std": 0.3932, "Agent": "REINFORCE"}, {"env_step": 7741440, "rew": -6.9134, "rew_std": 0.4837, "Agent": "REINFORCE"}, {"env_step": 7772160, "rew": -7.3976, "rew_std": 0.3856, "Agent": "REINFORCE"}, {"env_step": 7802880, "rew": -6.3811, "rew_std": 0.3291, "Agent": "REINFORCE"}, {"env_step": 7833600, "rew": -8.4398, "rew_std": 0.4035, "Agent": "REINFORCE"}, {"env_step": 7864320, "rew": -6.243, "rew_std": 0.3451, "Agent": "REINFORCE"}, {"env_step": 7895040, "rew": -7.9918, "rew_std": 0.5159, "Agent": "REINFORCE"}, {"env_step": 7925760, "rew": -7.4007, "rew_std": 0.6032, "Agent": "REINFORCE"}, {"env_step": 7956480, "rew": -7.2012, "rew_std": 0.3187, "Agent": "REINFORCE"}, {"env_step": 7987200, "rew": -7.2638, "rew_std": 0.2397, "Agent": "REINFORCE"}, {"env_step": 8017920, "rew": -6.9558, "rew_std": 0.2604, "Agent": "REINFORCE"}, {"env_step": 8048640, "rew": -7.0604, "rew_std": 0.4733, "Agent": "REINFORCE"}, {"env_step": 8079360, "rew": -6.3747, "rew_std": 0.3021, "Agent": "REINFORCE"}, {"env_step": 8110080, "rew": -6.4015, "rew_std": 0.2167, "Agent": "REINFORCE"}, {"env_step": 8140800, "rew": -7.0195, "rew_std": 0.5581, "Agent": "REINFORCE"}, {"env_step": 8171520, "rew": -6.7174, "rew_std": 0.2973, "Agent": "REINFORCE"}, {"env_step": 8202240, "rew": -6.6271, "rew_std": 0.2493, "Agent": "REINFORCE"}, {"env_step": 8232960, "rew": -6.8147, "rew_std": 0.4268, "Agent": "REINFORCE"}, {"env_step": 8263680, "rew": -6.5861, "rew_std": 0.2724, "Agent": "REINFORCE"}, {"env_step": 8294400, "rew": -7.1314, "rew_std": 0.3291, "Agent": "REINFORCE"}, {"env_step": 8325120, "rew": -6.4392, "rew_std": 0.4481, "Agent": "REINFORCE"}, {"env_step": 8355840, "rew": -6.304, "rew_std": 0.2563, "Agent": "REINFORCE"}, {"env_step": 8386560, "rew": -5.7995, "rew_std": 0.3314, "Agent": "REINFORCE"}, {"env_step": 8417280, "rew": -7.7415, "rew_std": 0.2744, "Agent": "REINFORCE"}, {"env_step": 8448000, "rew": -6.5171, "rew_std": 0.2879, "Agent": "REINFORCE"}, {"env_step": 8478720, "rew": -6.803, "rew_std": 0.4621, "Agent": "REINFORCE"}, {"env_step": 8509440, "rew": -7.1545, "rew_std": 0.4238, "Agent": "REINFORCE"}, {"env_step": 8540160, "rew": -7.0141, "rew_std": 0.5667, "Agent": "REINFORCE"}, {"env_step": 8570880, "rew": -7.498, "rew_std": 0.572, "Agent": "REINFORCE"}, {"env_step": 8601600, "rew": -6.8268, "rew_std": 0.1592, "Agent": "REINFORCE"}, {"env_step": 8632320, "rew": -7.1468, "rew_std": 1.0048, "Agent": "REINFORCE"}, {"env_step": 8663040, "rew": -6.231, "rew_std": 0.4246, "Agent": "REINFORCE"}, {"env_step": 8693760, "rew": -6.7758, "rew_std": 0.2444, "Agent": "REINFORCE"}, {"env_step": 8724480, "rew": -6.8614, "rew_std": 0.3005, "Agent": "REINFORCE"}, {"env_step": 8755200, "rew": -6.4715, "rew_std": 0.5622, "Agent": "REINFORCE"}, {"env_step": 8785920, "rew": -7.538, "rew_std": 0.33, "Agent": "REINFORCE"}, {"env_step": 8816640, "rew": -6.9378, "rew_std": 0.441, "Agent": "REINFORCE"}, {"env_step": 8847360, "rew": -7.0213, "rew_std": 0.4161, "Agent": "REINFORCE"}, {"env_step": 8878080, "rew": -6.3532, "rew_std": 0.2787, "Agent": "REINFORCE"}, {"env_step": 8908800, "rew": -5.9954, "rew_std": 0.4256, "Agent": "REINFORCE"}, {"env_step": 8939520, "rew": -6.4347, "rew_std": 0.337, "Agent": "REINFORCE"}, {"env_step": 8970240, "rew": -6.7357, "rew_std": 0.2993, "Agent": "REINFORCE"}, {"env_step": 9000960, "rew": -7.0348, "rew_std": 0.2923, "Agent": "REINFORCE"}, {"env_step": 9031680, "rew": -7.2234, "rew_std": 0.3924, "Agent": "REINFORCE"}, {"env_step": 9062400, "rew": -6.7263, "rew_std": 0.4882, "Agent": "REINFORCE"}, {"env_step": 9093120, "rew": -5.9239, "rew_std": 0.3753, "Agent": "REINFORCE"}, {"env_step": 9123840, "rew": -7.0764, "rew_std": 0.5975, "Agent": "REINFORCE"}, {"env_step": 9154560, "rew": -7.4387, "rew_std": 0.4296, "Agent": "REINFORCE"}, {"env_step": 9185280, "rew": -6.1808, "rew_std": 0.3834, "Agent": "REINFORCE"}, {"env_step": 9216000, "rew": -7.0908, "rew_std": 0.3954, "Agent": "REINFORCE"}, {"env_step": 9246720, "rew": -6.3499, "rew_std": 0.3025, "Agent": "REINFORCE"}, {"env_step": 9277440, "rew": -6.7003, "rew_std": 0.4033, "Agent": "REINFORCE"}, {"env_step": 9308160, "rew": -6.1223, "rew_std": 0.3594, "Agent": "REINFORCE"}, {"env_step": 9338880, "rew": -5.547, "rew_std": 0.2432, "Agent": "REINFORCE"}, {"env_step": 9369600, "rew": -6.7066, "rew_std": 0.2806, "Agent": "REINFORCE"}, {"env_step": 9400320, "rew": -6.4505, "rew_std": 0.4009, "Agent": "REINFORCE"}, {"env_step": 9431040, "rew": -6.6948, "rew_std": 0.4809, "Agent": "REINFORCE"}, {"env_step": 9461760, "rew": -6.4916, "rew_std": 0.2387, "Agent": "REINFORCE"}, {"env_step": 9492480, "rew": -6.337, "rew_std": 0.3624, "Agent": "REINFORCE"}, {"env_step": 9523200, "rew": -6.3873, "rew_std": 0.3239, "Agent": "REINFORCE"}, {"env_step": 9553920, "rew": -7.3367, "rew_std": 0.275, "Agent": "REINFORCE"}, {"env_step": 9584640, "rew": -6.1671, "rew_std": 0.3965, "Agent": "REINFORCE"}, {"env_step": 9615360, "rew": -6.2706, "rew_std": 0.3238, "Agent": "REINFORCE"}, {"env_step": 9646080, "rew": -6.1982, "rew_std": 0.5299, "Agent": "REINFORCE"}, {"env_step": 9676800, "rew": -6.5887, "rew_std": 0.4414, "Agent": "REINFORCE"}, {"env_step": 9707520, "rew": -7.471, "rew_std": 0.6133, "Agent": "REINFORCE"}, {"env_step": 9738240, "rew": -6.9098, "rew_std": 0.4671, "Agent": "REINFORCE"}, {"env_step": 9768960, "rew": -6.9614, "rew_std": 0.2386, "Agent": "REINFORCE"}, {"env_step": 9799680, "rew": -6.2465, "rew_std": 0.2412, "Agent": "REINFORCE"}, {"env_step": 9830400, "rew": -6.2565, "rew_std": 0.1699, "Agent": "REINFORCE"}, {"env_step": 9861120, "rew": -6.6373, "rew_std": 0.3563, "Agent": "REINFORCE"}, {"env_step": 9891840, "rew": -6.426, "rew_std": 0.3518, "Agent": "REINFORCE"}, {"env_step": 9922560, "rew": -6.5556, "rew_std": 0.3843, "Agent": "REINFORCE"}, {"env_step": 9953280, "rew": -6.0887, "rew_std": 0.323, "Agent": "REINFORCE"}, {"env_step": 9984000, "rew": -6.5108, "rew_std": 0.5198, "Agent": "REINFORCE"}, {"env_step": 10014720, "rew": -6.1655, "rew_std": 0.4087, "Agent": "REINFORCE"}, {"env_step": 10045440, "rew": -6.6196, "rew_std": 0.4188, "Agent": "REINFORCE"}, {"env_step": 10076160, "rew": -6.2191, "rew_std": 0.3846, "Agent": "REINFORCE"}, {"env_step": 10106880, "rew": -7.0509, "rew_std": 0.4208, "Agent": "REINFORCE"}, {"env_step": 10137600, "rew": -6.7348, "rew_std": 0.3687, "Agent": "REINFORCE"}, {"env_step": 10168320, "rew": -6.9149, "rew_std": 0.2471, "Agent": "REINFORCE"}, {"env_step": 10199040, "rew": -6.6179, "rew_std": 0.3684, "Agent": "REINFORCE"}, {"env_step": 10229760, "rew": -6.5823, "rew_std": 0.2693, "Agent": "REINFORCE"}, {"env_step": 0, "rew": -27.3232, "rew_std": 23.4601, "Agent": "SAC"}, {"env_step": 5000, "rew": -6.8932, "rew_std": 0.4332, "Agent": "SAC"}, {"env_step": 10000, "rew": -5.4257, "rew_std": 0.375, "Agent": "SAC"}, {"env_step": 15000, "rew": -4.6999, "rew_std": 0.3618, "Agent": "SAC"}, {"env_step": 20000, "rew": -3.9823, "rew_std": 0.2413, "Agent": "SAC"}, {"env_step": 25000, "rew": -4.8923, "rew_std": 0.2754, "Agent": "SAC"}, {"env_step": 30000, "rew": -3.9187, "rew_std": 0.2005, "Agent": "SAC"}, {"env_step": 35000, "rew": -4.0653, "rew_std": 0.1962, "Agent": "SAC"}, {"env_step": 40000, "rew": -4.2562, "rew_std": 0.2526, "Agent": "SAC"}, {"env_step": 45000, "rew": -4.049, "rew_std": 0.4252, "Agent": "SAC"}, {"env_step": 50000, "rew": -4.1731, "rew_std": 0.4454, "Agent": "SAC"}, {"env_step": 55000, "rew": -4.2256, "rew_std": 0.2316, "Agent": "SAC"}, {"env_step": 60000, "rew": -3.7714, "rew_std": 0.2894, "Agent": "SAC"}, {"env_step": 65000, "rew": -3.5403, "rew_std": 0.1666, "Agent": "SAC"}, {"env_step": 70000, "rew": -4.2174, "rew_std": 0.2763, "Agent": "SAC"}, {"env_step": 75000, "rew": -3.7467, "rew_std": 0.1565, "Agent": "SAC"}, {"env_step": 80000, "rew": -3.914, "rew_std": 0.2841, "Agent": "SAC"}, {"env_step": 85000, "rew": -3.8556, "rew_std": 0.1279, "Agent": "SAC"}, {"env_step": 90000, "rew": -4.6196, "rew_std": 0.3522, "Agent": "SAC"}, {"env_step": 95000, "rew": -4.0472, "rew_std": 0.1998, "Agent": "SAC"}, {"env_step": 100000, "rew": -4.2188, "rew_std": 0.2045, "Agent": "SAC"}, {"env_step": 105000, "rew": -4.2111, "rew_std": 0.3011, "Agent": "SAC"}, {"env_step": 110000, "rew": -4.4007, "rew_std": 0.307, "Agent": "SAC"}, {"env_step": 115000, "rew": -3.5302, "rew_std": 0.1679, "Agent": "SAC"}, {"env_step": 120000, "rew": -3.2939, "rew_std": 0.1955, "Agent": "SAC"}, {"env_step": 125000, "rew": -3.5366, "rew_std": 0.2136, "Agent": "SAC"}, {"env_step": 130000, "rew": -4.0446, "rew_std": 0.1986, "Agent": "SAC"}, {"env_step": 135000, "rew": -3.8398, "rew_std": 0.4702, "Agent": "SAC"}, {"env_step": 140000, "rew": -4.0787, "rew_std": 0.3272, "Agent": "SAC"}, {"env_step": 145000, "rew": -4.5688, "rew_std": 0.1852, "Agent": "SAC"}, {"env_step": 150000, "rew": -4.0183, "rew_std": 0.1741, "Agent": "SAC"}, {"env_step": 155000, "rew": -3.9579, "rew_std": 0.3947, "Agent": "SAC"}, {"env_step": 160000, "rew": -3.9063, "rew_std": 0.2715, "Agent": "SAC"}, {"env_step": 165000, "rew": -4.0287, "rew_std": 0.3581, "Agent": "SAC"}, {"env_step": 170000, "rew": -4.0284, "rew_std": 0.1758, "Agent": "SAC"}, {"env_step": 175000, "rew": -3.9873, "rew_std": 0.2332, "Agent": "SAC"}, {"env_step": 180000, "rew": -4.0801, "rew_std": 0.1964, "Agent": "SAC"}, {"env_step": 185000, "rew": -3.5858, "rew_std": 0.2554, "Agent": "SAC"}, {"env_step": 190000, "rew": -3.8319, "rew_std": 0.2312, "Agent": "SAC"}, {"env_step": 195000, "rew": -3.54, "rew_std": 0.2315, "Agent": "SAC"}, {"env_step": 200000, "rew": -3.5242, "rew_std": 0.2424, "Agent": "SAC"}, {"env_step": 205000, "rew": -3.9358, "rew_std": 0.2275, "Agent": "SAC"}, {"env_step": 210000, "rew": -4.133, "rew_std": 0.1878, "Agent": "SAC"}, {"env_step": 215000, "rew": -4.2018, "rew_std": 0.1802, "Agent": "SAC"}, {"env_step": 220000, "rew": -3.6076, "rew_std": 0.2573, "Agent": "SAC"}, {"env_step": 225000, "rew": -4.0694, "rew_std": 0.1866, "Agent": "SAC"}, {"env_step": 230000, "rew": -4.0068, "rew_std": 0.171, "Agent": "SAC"}, {"env_step": 235000, "rew": -3.1935, "rew_std": 0.2678, "Agent": "SAC"}, {"env_step": 240000, "rew": -4.2044, "rew_std": 0.2314, "Agent": "SAC"}, {"env_step": 245000, "rew": -3.9757, "rew_std": 0.2236, "Agent": "SAC"}, {"env_step": 250000, "rew": -3.853, "rew_std": 0.2918, "Agent": "SAC"}, {"env_step": 255000, "rew": -3.3434, "rew_std": 0.2674, "Agent": "SAC"}, {"env_step": 260000, "rew": -3.803, "rew_std": 0.076, "Agent": "SAC"}, {"env_step": 265000, "rew": -3.6264, "rew_std": 0.2275, "Agent": "SAC"}, {"env_step": 270000, "rew": -3.7682, "rew_std": 0.2303, "Agent": "SAC"}, {"env_step": 275000, "rew": -3.6978, "rew_std": 0.2235, "Agent": "SAC"}, {"env_step": 280000, "rew": -3.7764, "rew_std": 0.2653, "Agent": "SAC"}, {"env_step": 285000, "rew": -4.1724, "rew_std": 0.1296, "Agent": "SAC"}, {"env_step": 290000, "rew": -3.4387, "rew_std": 0.1367, "Agent": "SAC"}, {"env_step": 295000, "rew": -3.498, "rew_std": 0.1265, "Agent": "SAC"}, {"env_step": 300000, "rew": -3.6395, "rew_std": 0.4138, "Agent": "SAC"}, {"env_step": 305000, "rew": -3.5984, "rew_std": 0.1731, "Agent": "SAC"}, {"env_step": 310000, "rew": -4.015, "rew_std": 0.2282, "Agent": "SAC"}, {"env_step": 315000, "rew": -3.95, "rew_std": 0.1787, "Agent": "SAC"}, {"env_step": 320000, "rew": -3.3073, "rew_std": 0.3131, "Agent": "SAC"}, {"env_step": 325000, "rew": -4.1756, "rew_std": 0.3148, "Agent": "SAC"}, {"env_step": 330000, "rew": -3.9191, "rew_std": 0.2974, "Agent": "SAC"}, {"env_step": 335000, "rew": -3.4546, "rew_std": 0.2539, "Agent": "SAC"}, {"env_step": 340000, "rew": -3.4146, "rew_std": 0.2075, "Agent": "SAC"}, {"env_step": 345000, "rew": -3.7292, "rew_std": 0.2684, "Agent": "SAC"}, {"env_step": 350000, "rew": -3.7271, "rew_std": 0.2108, "Agent": "SAC"}, {"env_step": 355000, "rew": -2.995, "rew_std": 0.2411, "Agent": "SAC"}, {"env_step": 360000, "rew": -3.5224, "rew_std": 0.3234, "Agent": "SAC"}, {"env_step": 365000, "rew": -4.4527, "rew_std": 0.1725, "Agent": "SAC"}, {"env_step": 370000, "rew": -3.5645, "rew_std": 0.2728, "Agent": "SAC"}, {"env_step": 375000, "rew": -3.9574, "rew_std": 0.2716, "Agent": "SAC"}, {"env_step": 380000, "rew": -4.0055, "rew_std": 0.2029, "Agent": "SAC"}, {"env_step": 385000, "rew": -3.7493, "rew_std": 0.3596, "Agent": "SAC"}, {"env_step": 390000, "rew": -4.5829, "rew_std": 0.2336, "Agent": "SAC"}, {"env_step": 395000, "rew": -3.7456, "rew_std": 0.3923, "Agent": "SAC"}, {"env_step": 400000, "rew": -3.6572, "rew_std": 0.1587, "Agent": "SAC"}, {"env_step": 405000, "rew": -4.0184, "rew_std": 0.2194, "Agent": "SAC"}, {"env_step": 410000, "rew": -3.9406, "rew_std": 0.1733, "Agent": "SAC"}, {"env_step": 415000, "rew": -3.7399, "rew_std": 0.1998, "Agent": "SAC"}, {"env_step": 420000, "rew": -3.9239, "rew_std": 0.2568, "Agent": "SAC"}, {"env_step": 425000, "rew": -4.1145, "rew_std": 0.1507, "Agent": "SAC"}, {"env_step": 430000, "rew": -3.7682, "rew_std": 0.173, "Agent": "SAC"}, {"env_step": 435000, "rew": -4.1476, "rew_std": 0.1799, "Agent": "SAC"}, {"env_step": 440000, "rew": -3.9612, "rew_std": 0.3424, "Agent": "SAC"}, {"env_step": 445000, "rew": -3.6732, "rew_std": 0.2416, "Agent": "SAC"}, {"env_step": 450000, "rew": -3.7399, "rew_std": 0.3562, "Agent": "SAC"}, {"env_step": 455000, "rew": -3.2862, "rew_std": 0.2323, "Agent": "SAC"}, {"env_step": 460000, "rew": -3.7226, "rew_std": 0.163, "Agent": "SAC"}, {"env_step": 465000, "rew": -3.9655, "rew_std": 0.299, "Agent": "SAC"}, {"env_step": 470000, "rew": -3.5547, "rew_std": 0.2374, "Agent": "SAC"}, {"env_step": 475000, "rew": -3.2005, "rew_std": 0.4062, "Agent": "SAC"}, {"env_step": 480000, "rew": -3.9225, "rew_std": 0.2044, "Agent": "SAC"}, {"env_step": 485000, "rew": -3.9684, "rew_std": 0.2615, "Agent": "SAC"}, {"env_step": 490000, "rew": -3.2122, "rew_std": 0.3031, "Agent": "SAC"}, {"env_step": 495000, "rew": -3.853, "rew_std": 0.1553, "Agent": "SAC"}, {"env_step": 500000, "rew": -3.7073, "rew_std": 0.2017, "Agent": "SAC"}, {"env_step": 505000, "rew": -4.1796, "rew_std": 0.4032, "Agent": "SAC"}, {"env_step": 510000, "rew": -3.6917, "rew_std": 0.2682, "Agent": "SAC"}, {"env_step": 515000, "rew": -3.8461, "rew_std": 0.2467, "Agent": "SAC"}, {"env_step": 520000, "rew": -3.9398, "rew_std": 0.2085, "Agent": "SAC"}, {"env_step": 525000, "rew": -3.7744, "rew_std": 0.2113, "Agent": "SAC"}, {"env_step": 530000, "rew": -3.2922, "rew_std": 0.0859, "Agent": "SAC"}, {"env_step": 535000, "rew": -4.3306, "rew_std": 0.2415, "Agent": "SAC"}, {"env_step": 540000, "rew": -3.5895, "rew_std": 0.2116, "Agent": "SAC"}, {"env_step": 545000, "rew": -3.4097, "rew_std": 0.2857, "Agent": "SAC"}, {"env_step": 550000, "rew": -4.1661, "rew_std": 0.4291, "Agent": "SAC"}, {"env_step": 555000, "rew": -3.8228, "rew_std": 0.261, "Agent": "SAC"}, {"env_step": 560000, "rew": -3.3382, "rew_std": 0.1074, "Agent": "SAC"}, {"env_step": 565000, "rew": -4.3171, "rew_std": 0.3027, "Agent": "SAC"}, {"env_step": 570000, "rew": -3.3844, "rew_std": 0.1957, "Agent": "SAC"}, {"env_step": 575000, "rew": -4.0007, "rew_std": 0.2696, "Agent": "SAC"}, {"env_step": 580000, "rew": -3.264, "rew_std": 0.2616, "Agent": "SAC"}, {"env_step": 585000, "rew": -3.1616, "rew_std": 0.2267, "Agent": "SAC"}, {"env_step": 590000, "rew": -3.2486, "rew_std": 0.1327, "Agent": "SAC"}, {"env_step": 595000, "rew": -3.2078, "rew_std": 0.3255, "Agent": "SAC"}, {"env_step": 600000, "rew": -3.9192, "rew_std": 0.2526, "Agent": "SAC"}, {"env_step": 605000, "rew": -3.8578, "rew_std": 0.1864, "Agent": "SAC"}, {"env_step": 610000, "rew": -4.6848, "rew_std": 0.284, "Agent": "SAC"}, {"env_step": 615000, "rew": -3.9151, "rew_std": 0.2585, "Agent": "SAC"}, {"env_step": 620000, "rew": -4.4256, "rew_std": 0.094, "Agent": "SAC"}, {"env_step": 625000, "rew": -3.5401, "rew_std": 0.4503, "Agent": "SAC"}, {"env_step": 630000, "rew": -3.524, "rew_std": 0.4818, "Agent": "SAC"}, {"env_step": 635000, "rew": -3.442, "rew_std": 0.1696, "Agent": "SAC"}, {"env_step": 640000, "rew": -3.5255, "rew_std": 0.2712, "Agent": "SAC"}, {"env_step": 645000, "rew": -3.782, "rew_std": 0.2156, "Agent": "SAC"}, {"env_step": 650000, "rew": -3.1343, "rew_std": 0.3479, "Agent": "SAC"}, {"env_step": 655000, "rew": -3.8279, "rew_std": 0.2866, "Agent": "SAC"}, {"env_step": 660000, "rew": -4.1674, "rew_std": 0.1903, "Agent": "SAC"}, {"env_step": 665000, "rew": -3.9484, "rew_std": 0.1277, "Agent": "SAC"}, {"env_step": 670000, "rew": -3.5213, "rew_std": 0.3465, "Agent": "SAC"}, {"env_step": 675000, "rew": -3.7349, "rew_std": 0.1057, "Agent": "SAC"}, {"env_step": 680000, "rew": -3.3612, "rew_std": 0.3636, "Agent": "SAC"}, {"env_step": 685000, "rew": -3.8076, "rew_std": 0.3608, "Agent": "SAC"}, {"env_step": 690000, "rew": -3.1594, "rew_std": 0.2127, "Agent": "SAC"}, {"env_step": 695000, "rew": -3.5717, "rew_std": 0.2468, "Agent": "SAC"}, {"env_step": 700000, "rew": -4.2846, "rew_std": 0.3269, "Agent": "SAC"}, {"env_step": 705000, "rew": -2.6392, "rew_std": 0.1967, "Agent": "SAC"}, {"env_step": 710000, "rew": -3.9591, "rew_std": 0.1954, "Agent": "SAC"}, {"env_step": 715000, "rew": -3.8285, "rew_std": 0.1842, "Agent": "SAC"}, {"env_step": 720000, "rew": -4.1874, "rew_std": 0.2372, "Agent": "SAC"}, {"env_step": 725000, "rew": -4.23, "rew_std": 0.2298, "Agent": "SAC"}, {"env_step": 730000, "rew": -3.9943, "rew_std": 0.1125, "Agent": "SAC"}, {"env_step": 735000, "rew": -4.2428, "rew_std": 0.382, "Agent": "SAC"}, {"env_step": 740000, "rew": -3.284, "rew_std": 0.1734, "Agent": "SAC"}, {"env_step": 745000, "rew": -4.3527, "rew_std": 0.3046, "Agent": "SAC"}, {"env_step": 750000, "rew": -3.7276, "rew_std": 0.2788, "Agent": "SAC"}, {"env_step": 755000, "rew": -3.853, "rew_std": 0.2585, "Agent": "SAC"}, {"env_step": 760000, "rew": -4.1638, "rew_std": 0.1737, "Agent": "SAC"}, {"env_step": 765000, "rew": -3.8378, "rew_std": 0.3044, "Agent": "SAC"}, {"env_step": 770000, "rew": -3.6317, "rew_std": 0.1868, "Agent": "SAC"}, {"env_step": 775000, "rew": -3.1226, "rew_std": 0.3625, "Agent": "SAC"}, {"env_step": 780000, "rew": -3.2461, "rew_std": 0.1901, "Agent": "SAC"}, {"env_step": 785000, "rew": -3.7067, "rew_std": 0.2888, "Agent": "SAC"}, {"env_step": 790000, "rew": -3.6783, "rew_std": 0.1692, "Agent": "SAC"}, {"env_step": 795000, "rew": -4.1268, "rew_std": 0.2453, "Agent": "SAC"}, {"env_step": 800000, "rew": -4.0306, "rew_std": 0.1147, "Agent": "SAC"}, {"env_step": 805000, "rew": -3.8568, "rew_std": 0.1906, "Agent": "SAC"}, {"env_step": 810000, "rew": -3.9614, "rew_std": 0.1425, "Agent": "SAC"}, {"env_step": 815000, "rew": -3.5216, "rew_std": 0.2319, "Agent": "SAC"}, {"env_step": 820000, "rew": -4.1455, "rew_std": 0.1742, "Agent": "SAC"}, {"env_step": 825000, "rew": -3.7852, "rew_std": 0.2343, "Agent": "SAC"}, {"env_step": 830000, "rew": -3.8092, "rew_std": 0.3493, "Agent": "SAC"}, {"env_step": 835000, "rew": -3.9306, "rew_std": 0.2396, "Agent": "SAC"}, {"env_step": 840000, "rew": -3.3459, "rew_std": 0.1771, "Agent": "SAC"}, {"env_step": 845000, "rew": -3.8375, "rew_std": 0.2289, "Agent": "SAC"}, {"env_step": 850000, "rew": -3.773, "rew_std": 0.334, "Agent": "SAC"}, {"env_step": 855000, "rew": -3.7423, "rew_std": 0.1455, "Agent": "SAC"}, {"env_step": 860000, "rew": -3.5717, "rew_std": 0.2908, "Agent": "SAC"}, {"env_step": 865000, "rew": -3.793, "rew_std": 0.2614, "Agent": "SAC"}, {"env_step": 870000, "rew": -3.9901, "rew_std": 0.1795, "Agent": "SAC"}, {"env_step": 875000, "rew": -3.3035, "rew_std": 0.1585, "Agent": "SAC"}, {"env_step": 880000, "rew": -3.9038, "rew_std": 0.1819, "Agent": "SAC"}, {"env_step": 885000, "rew": -3.6178, "rew_std": 0.1359, "Agent": "SAC"}, {"env_step": 890000, "rew": -3.048, "rew_std": 0.3071, "Agent": "SAC"}, {"env_step": 895000, "rew": -3.4024, "rew_std": 0.3728, "Agent": "SAC"}, {"env_step": 900000, "rew": -3.0424, "rew_std": 0.1856, "Agent": "SAC"}, {"env_step": 905000, "rew": -4.4867, "rew_std": 0.2158, "Agent": "SAC"}, {"env_step": 910000, "rew": -3.9053, "rew_std": 0.3731, "Agent": "SAC"}, {"env_step": 915000, "rew": -3.8313, "rew_std": 0.2227, "Agent": "SAC"}, {"env_step": 920000, "rew": -4.0479, "rew_std": 0.3955, "Agent": "SAC"}, {"env_step": 925000, "rew": -3.2882, "rew_std": 0.2191, "Agent": "SAC"}, {"env_step": 930000, "rew": -3.6986, "rew_std": 0.3256, "Agent": "SAC"}, {"env_step": 935000, "rew": -4.0628, "rew_std": 0.3019, "Agent": "SAC"}, {"env_step": 940000, "rew": -3.9745, "rew_std": 0.2697, "Agent": "SAC"}, {"env_step": 945000, "rew": -3.6575, "rew_std": 0.2834, "Agent": "SAC"}, {"env_step": 950000, "rew": -3.6307, "rew_std": 0.3706, "Agent": "SAC"}, {"env_step": 955000, "rew": -3.4208, "rew_std": 0.1648, "Agent": "SAC"}, {"env_step": 960000, "rew": -3.3755, "rew_std": 0.286, "Agent": "SAC"}, {"env_step": 965000, "rew": -3.663, "rew_std": 0.2868, "Agent": "SAC"}, {"env_step": 970000, "rew": -4.1586, "rew_std": 0.1768, "Agent": "SAC"}, {"env_step": 975000, "rew": -4.092, "rew_std": 0.1419, "Agent": "SAC"}, {"env_step": 980000, "rew": -4.132, "rew_std": 0.3045, "Agent": "SAC"}, {"env_step": 985000, "rew": -3.7042, "rew_std": 0.3782, "Agent": "SAC"}, {"env_step": 990000, "rew": -2.9588, "rew_std": 0.2477, "Agent": "SAC"}, {"env_step": 995000, "rew": -3.1927, "rew_std": 0.1776, "Agent": "SAC"}, {"env_step": 1000000, "rew": -3.8197, "rew_std": 0.2444, "Agent": "SAC"}, {"env_step": 1005000, "rew": -4.0601, "rew_std": 0.1803, "Agent": "SAC"}, {"env_step": 1010000, "rew": -2.9736, "rew_std": 0.1404, "Agent": "SAC"}, {"env_step": 1015000, "rew": -4.093, "rew_std": 0.327, "Agent": "SAC"}, {"env_step": 1020000, "rew": -3.9777, "rew_std": 0.3032, "Agent": "SAC"}, {"env_step": 1025000, "rew": -4.2207, "rew_std": 0.1991, "Agent": "SAC"}, {"env_step": 1030000, "rew": -4.2962, "rew_std": 0.2042, "Agent": "SAC"}, {"env_step": 1035000, "rew": -3.8344, "rew_std": 0.1368, "Agent": "SAC"}, {"env_step": 1040000, "rew": -4.1522, "rew_std": 0.2222, "Agent": "SAC"}, {"env_step": 1045000, "rew": -3.6833, "rew_std": 0.2655, "Agent": "SAC"}, {"env_step": 1050000, "rew": -3.1982, "rew_std": 0.2894, "Agent": "SAC"}, {"env_step": 1055000, "rew": -3.9271, "rew_std": 0.4604, "Agent": "SAC"}, {"env_step": 1060000, "rew": -3.7066, "rew_std": 0.2758, "Agent": "SAC"}, {"env_step": 1065000, "rew": -4.0772, "rew_std": 0.1879, "Agent": "SAC"}, {"env_step": 1070000, "rew": -3.707, "rew_std": 0.1503, "Agent": "SAC"}, {"env_step": 1075000, "rew": -2.8186, "rew_std": 0.3516, "Agent": "SAC"}, {"env_step": 1080000, "rew": -3.5769, "rew_std": 0.0814, "Agent": "SAC"}, {"env_step": 1085000, "rew": -3.9369, "rew_std": 0.1667, "Agent": "SAC"}, {"env_step": 1090000, "rew": -3.199, "rew_std": 0.2651, "Agent": "SAC"}, {"env_step": 1095000, "rew": -3.452, "rew_std": 0.268, "Agent": "SAC"}, {"env_step": 1100000, "rew": -4.5154, "rew_std": 0.303, "Agent": "SAC"}, {"env_step": 1105000, "rew": -3.4344, "rew_std": 0.1963, "Agent": "SAC"}, {"env_step": 1110000, "rew": -4.3523, "rew_std": 0.2202, "Agent": "SAC"}, {"env_step": 1115000, "rew": -4.0188, "rew_std": 0.2337, "Agent": "SAC"}, {"env_step": 1120000, "rew": -4.0969, "rew_std": 0.478, "Agent": "SAC"}, {"env_step": 1125000, "rew": -3.6457, "rew_std": 0.2369, "Agent": "SAC"}, {"env_step": 1130000, "rew": -4.2586, "rew_std": 0.3208, "Agent": "SAC"}, {"env_step": 1135000, "rew": -3.4311, "rew_std": 0.1391, "Agent": "SAC"}, {"env_step": 1140000, "rew": -3.7406, "rew_std": 0.2248, "Agent": "SAC"}, {"env_step": 1145000, "rew": -3.6664, "rew_std": 0.152, "Agent": "SAC"}, {"env_step": 1150000, "rew": -3.6026, "rew_std": 0.2842, "Agent": "SAC"}, {"env_step": 1155000, "rew": -3.9512, "rew_std": 0.1563, "Agent": "SAC"}, {"env_step": 1160000, "rew": -3.2359, "rew_std": 0.2899, "Agent": "SAC"}, {"env_step": 1165000, "rew": -4.352, "rew_std": 0.4036, "Agent": "SAC"}, {"env_step": 1170000, "rew": -4.4763, "rew_std": 0.4422, "Agent": "SAC"}, {"env_step": 1175000, "rew": -2.887, "rew_std": 0.1978, "Agent": "SAC"}, {"env_step": 1180000, "rew": -3.366, "rew_std": 0.1115, "Agent": "SAC"}, {"env_step": 1185000, "rew": -3.7818, "rew_std": 0.3499, "Agent": "SAC"}, {"env_step": 1190000, "rew": -4.2838, "rew_std": 0.2112, "Agent": "SAC"}, {"env_step": 1195000, "rew": -3.8644, "rew_std": 0.1579, "Agent": "SAC"}, {"env_step": 1200000, "rew": -3.9126, "rew_std": 0.3867, "Agent": "SAC"}, {"env_step": 1205000, "rew": -3.6113, "rew_std": 0.1608, "Agent": "SAC"}, {"env_step": 1210000, "rew": -3.6634, "rew_std": 0.3782, "Agent": "SAC"}, {"env_step": 1215000, "rew": -3.469, "rew_std": 0.3198, "Agent": "SAC"}, {"env_step": 1220000, "rew": -3.9637, "rew_std": 0.3019, "Agent": "SAC"}, {"env_step": 1225000, "rew": -3.3988, "rew_std": 0.1586, "Agent": "SAC"}, {"env_step": 1230000, "rew": -3.798, "rew_std": 0.157, "Agent": "SAC"}, {"env_step": 1235000, "rew": -4.1499, "rew_std": 0.111, "Agent": "SAC"}, {"env_step": 1240000, "rew": -3.4294, "rew_std": 0.2204, "Agent": "SAC"}, {"env_step": 1245000, "rew": -3.9595, "rew_std": 0.1531, "Agent": "SAC"}, {"env_step": 1250000, "rew": -4.1026, "rew_std": 0.2315, "Agent": "SAC"}, {"env_step": 0, "rew": -39.7236, "rew_std": 1.6682, "Agent": "TRPO"}, {"env_step": 30720, "rew": -27.9901, "rew_std": 2.1268, "Agent": "TRPO"}, {"env_step": 61440, "rew": -13.1535, "rew_std": 1.2947, "Agent": "TRPO"}, {"env_step": 92160, "rew": -10.7569, "rew_std": 1.9249, "Agent": "TRPO"}, {"env_step": 122880, "rew": -7.3569, "rew_std": 1.3214, "Agent": "TRPO"}, {"env_step": 153600, "rew": -8.0953, "rew_std": 0.8433, "Agent": "TRPO"}, {"env_step": 184320, "rew": -8.3318, "rew_std": 1.3155, "Agent": "TRPO"}, {"env_step": 215040, "rew": -8.5948, "rew_std": 1.41, "Agent": "TRPO"}, {"env_step": 245760, "rew": -7.4731, "rew_std": 0.9133, "Agent": "TRPO"}, {"env_step": 276480, "rew": -7.955, "rew_std": 1.1796, "Agent": "TRPO"}, {"env_step": 307200, "rew": -6.4938, "rew_std": 0.6919, "Agent": "TRPO"}, {"env_step": 337920, "rew": -7.2835, "rew_std": 0.9598, "Agent": "TRPO"}, {"env_step": 368640, "rew": -8.0603, "rew_std": 0.7904, "Agent": "TRPO"}, {"env_step": 399360, "rew": -6.9808, "rew_std": 0.8146, "Agent": "TRPO"}, {"env_step": 430080, "rew": -6.7812, "rew_std": 0.6315, "Agent": "TRPO"}, {"env_step": 460800, "rew": -6.3235, "rew_std": 0.548, "Agent": "TRPO"}, {"env_step": 491520, "rew": -6.1458, "rew_std": 0.7332, "Agent": "TRPO"}, {"env_step": 522240, "rew": -6.7496, "rew_std": 0.9168, "Agent": "TRPO"}, {"env_step": 552960, "rew": -6.9758, "rew_std": 0.3431, "Agent": "TRPO"}, {"env_step": 583680, "rew": -7.4856, "rew_std": 0.5909, "Agent": "TRPO"}, {"env_step": 614400, "rew": -7.0599, "rew_std": 0.6794, "Agent": "TRPO"}, {"env_step": 645120, "rew": -6.1955, "rew_std": 0.4989, "Agent": "TRPO"}, {"env_step": 675840, "rew": -7.3452, "rew_std": 1.1674, "Agent": "TRPO"}, {"env_step": 706560, "rew": -6.2682, "rew_std": 0.7826, "Agent": "TRPO"}, {"env_step": 737280, "rew": -5.3892, "rew_std": 0.7166, "Agent": "TRPO"}, {"env_step": 768000, "rew": -5.8096, "rew_std": 0.5522, "Agent": "TRPO"}, {"env_step": 798720, "rew": -5.8967, "rew_std": 0.6513, "Agent": "TRPO"}, {"env_step": 829440, "rew": -6.2282, "rew_std": 0.7413, "Agent": "TRPO"}, {"env_step": 860160, "rew": -5.9055, "rew_std": 0.9823, "Agent": "TRPO"}, {"env_step": 890880, "rew": -5.7394, "rew_std": 0.8302, "Agent": "TRPO"}, {"env_step": 921600, "rew": -5.3251, "rew_std": 0.5898, "Agent": "TRPO"}, {"env_step": 952320, "rew": -5.0895, "rew_std": 0.7849, "Agent": "TRPO"}, {"env_step": 983040, "rew": -5.5538, "rew_std": 0.5979, "Agent": "TRPO"}, {"env_step": 1013760, "rew": -5.6917, "rew_std": 1.1224, "Agent": "TRPO"}, {"env_step": 1044480, "rew": -5.1366, "rew_std": 0.8106, "Agent": "TRPO"}, {"env_step": 1075200, "rew": -5.3292, "rew_std": 0.4762, "Agent": "TRPO"}, {"env_step": 1105920, "rew": -5.4226, "rew_std": 0.8731, "Agent": "TRPO"}, {"env_step": 1136640, "rew": -5.5528, "rew_std": 0.9979, "Agent": "TRPO"}, {"env_step": 1167360, "rew": -5.129, "rew_std": 0.6216, "Agent": "TRPO"}, {"env_step": 1198080, "rew": -5.0808, "rew_std": 0.7679, "Agent": "TRPO"}, {"env_step": 1228800, "rew": -5.88, "rew_std": 0.8018, "Agent": "TRPO"}, {"env_step": 1259520, "rew": -5.5796, "rew_std": 0.6684, "Agent": "TRPO"}, {"env_step": 1290240, "rew": -5.3655, "rew_std": 0.8384, "Agent": "TRPO"}, {"env_step": 1320960, "rew": -5.9151, "rew_std": 1.1241, "Agent": "TRPO"}, {"env_step": 1351680, "rew": -5.2118, "rew_std": 1.026, "Agent": "TRPO"}, {"env_step": 1382400, "rew": -4.7424, "rew_std": 0.6458, "Agent": "TRPO"}, {"env_step": 1413120, "rew": -4.4509, "rew_std": 0.7657, "Agent": "TRPO"}, {"env_step": 1443840, "rew": -3.8998, "rew_std": 0.3802, "Agent": "TRPO"}, {"env_step": 1474560, "rew": -5.0705, "rew_std": 0.7326, "Agent": "TRPO"}, {"env_step": 1505280, "rew": -4.7462, "rew_std": 0.8837, "Agent": "TRPO"}, {"env_step": 1536000, "rew": -4.6216, "rew_std": 0.7755, "Agent": "TRPO"}, {"env_step": 1566720, "rew": -5.4447, "rew_std": 0.543, "Agent": "TRPO"}, {"env_step": 1597440, "rew": -5.2095, "rew_std": 0.7103, "Agent": "TRPO"}, {"env_step": 1628160, "rew": -4.9382, "rew_std": 0.8371, "Agent": "TRPO"}, {"env_step": 1658880, "rew": -4.6101, "rew_std": 0.6448, "Agent": "TRPO"}, {"env_step": 1689600, "rew": -5.0216, "rew_std": 0.9348, "Agent": "TRPO"}, {"env_step": 1720320, "rew": -4.1787, "rew_std": 0.7827, "Agent": "TRPO"}, {"env_step": 1751040, "rew": -4.875, "rew_std": 0.8802, "Agent": "TRPO"}, {"env_step": 1781760, "rew": -4.2316, "rew_std": 0.5534, "Agent": "TRPO"}, {"env_step": 1812480, "rew": -4.9535, "rew_std": 0.6345, "Agent": "TRPO"}, {"env_step": 1843200, "rew": -4.4624, "rew_std": 0.4206, "Agent": "TRPO"}, {"env_step": 1873920, "rew": -4.9411, "rew_std": 0.7707, "Agent": "TRPO"}, {"env_step": 1904640, "rew": -4.2452, "rew_std": 0.6093, "Agent": "TRPO"}, {"env_step": 1935360, "rew": -4.3014, "rew_std": 0.6598, "Agent": "TRPO"}, {"env_step": 1966080, "rew": -5.1562, "rew_std": 0.6909, "Agent": "TRPO"}, {"env_step": 1996800, "rew": -4.1514, "rew_std": 0.6976, "Agent": "TRPO"}, {"env_step": 2027520, "rew": -4.6391, "rew_std": 0.8236, "Agent": "TRPO"}, {"env_step": 2058240, "rew": -5.5955, "rew_std": 1.1023, "Agent": "TRPO"}, {"env_step": 2088960, "rew": -5.1031, "rew_std": 1.1237, "Agent": "TRPO"}, {"env_step": 2119680, "rew": -4.9049, "rew_std": 0.9173, "Agent": "TRPO"}, {"env_step": 2150400, "rew": -5.0871, "rew_std": 0.6856, "Agent": "TRPO"}, {"env_step": 2181120, "rew": -5.6492, "rew_std": 0.9966, "Agent": "TRPO"}, {"env_step": 2211840, "rew": -4.269, "rew_std": 0.6294, "Agent": "TRPO"}, {"env_step": 2242560, "rew": -5.4708, "rew_std": 1.2603, "Agent": "TRPO"}, {"env_step": 2273280, "rew": -4.5029, "rew_std": 0.679, "Agent": "TRPO"}, {"env_step": 2304000, "rew": -5.264, "rew_std": 0.6552, "Agent": "TRPO"}, {"env_step": 2334720, "rew": -4.8189, "rew_std": 1.054, "Agent": "TRPO"}, {"env_step": 2365440, "rew": -3.91, "rew_std": 0.571, "Agent": "TRPO"}, {"env_step": 2396160, "rew": -5.0469, "rew_std": 0.9287, "Agent": "TRPO"}, {"env_step": 2426880, "rew": -3.924, "rew_std": 0.532, "Agent": "TRPO"}, {"env_step": 2457600, "rew": -4.7974, "rew_std": 0.6148, "Agent": "TRPO"}, {"env_step": 2488320, "rew": -5.9802, "rew_std": 1.3895, "Agent": "TRPO"}, {"env_step": 2519040, "rew": -4.3438, "rew_std": 0.658, "Agent": "TRPO"}, {"env_step": 2549760, "rew": -4.5274, "rew_std": 1.1324, "Agent": "TRPO"}, {"env_step": 2580480, "rew": -5.0352, "rew_std": 0.8565, "Agent": "TRPO"}, {"env_step": 2611200, "rew": -4.4126, "rew_std": 0.8215, "Agent": "TRPO"}, {"env_step": 2641920, "rew": -3.9125, "rew_std": 0.6613, "Agent": "TRPO"}, {"env_step": 2672640, "rew": -4.7159, "rew_std": 0.8097, "Agent": "TRPO"}, {"env_step": 2703360, "rew": -4.1105, "rew_std": 0.5076, "Agent": "TRPO"}, {"env_step": 2734080, "rew": -4.1588, "rew_std": 0.5627, "Agent": "TRPO"}, {"env_step": 2764800, "rew": -4.7868, "rew_std": 0.8906, "Agent": "TRPO"}, {"env_step": 2795520, "rew": -4.569, "rew_std": 0.6083, "Agent": "TRPO"}, {"env_step": 2826240, "rew": -4.4699, "rew_std": 0.7314, "Agent": "TRPO"}, {"env_step": 2856960, "rew": -5.3493, "rew_std": 0.7719, "Agent": "TRPO"}, {"env_step": 2887680, "rew": -4.5021, "rew_std": 0.692, "Agent": "TRPO"}, {"env_step": 2918400, "rew": -4.5991, "rew_std": 0.5796, "Agent": "TRPO"}, {"env_step": 2949120, "rew": -4.409, "rew_std": 0.5492, "Agent": "TRPO"}, {"env_step": 2979840, "rew": -4.7796, "rew_std": 0.7587, "Agent": "TRPO"}, {"env_step": 3010560, "rew": -4.2482, "rew_std": 0.5504, "Agent": "TRPO"}, {"env_step": 3041280, "rew": -5.2515, "rew_std": 1.0087, "Agent": "TRPO"}, {"env_step": 3072000, "rew": -5.0596, "rew_std": 0.7906, "Agent": "TRPO"}, {"env_step": 0, "rew": -39.7236, "rew_std": 1.6682, "Agent": "A2C"}, {"env_step": 30000, "rew": -49.5126, "rew_std": 6.7796, "Agent": "A2C"}, {"env_step": 60000, "rew": -47.0013, "rew_std": 14.3514, "Agent": "A2C"}, {"env_step": 90000, "rew": -35.2423, "rew_std": 16.0327, "Agent": "A2C"}, {"env_step": 120000, "rew": -27.4804, "rew_std": 15.9979, "Agent": "A2C"}, {"env_step": 150000, "rew": -23.4895, "rew_std": 16.217, "Agent": "A2C"}, {"env_step": 180000, "rew": -21.7784, "rew_std": 15.5391, "Agent": "A2C"}, {"env_step": 210000, "rew": -19.4302, "rew_std": 14.4032, "Agent": "A2C"}, {"env_step": 240000, "rew": -17.3468, "rew_std": 15.2334, "Agent": "A2C"}, {"env_step": 270000, "rew": -16.9129, "rew_std": 16.6739, "Agent": "A2C"}, {"env_step": 300000, "rew": -15.4613, "rew_std": 16.6621, "Agent": "A2C"}, {"env_step": 330000, "rew": -15.2061, "rew_std": 15.9173, "Agent": "A2C"}, {"env_step": 360000, "rew": -15.8345, "rew_std": 15.892, "Agent": "A2C"}, {"env_step": 390000, "rew": -12.0236, "rew_std": 8.8214, "Agent": "A2C"}, {"env_step": 420000, "rew": -10.2533, "rew_std": 3.8797, "Agent": "A2C"}, {"env_step": 450000, "rew": -9.3766, "rew_std": 2.3657, "Agent": "A2C"}, {"env_step": 480000, "rew": -8.8854, "rew_std": 2.9041, "Agent": "A2C"}, {"env_step": 510000, "rew": -9.0523, "rew_std": 1.5466, "Agent": "A2C"}, {"env_step": 540000, "rew": -9.4109, "rew_std": 1.291, "Agent": "A2C"}, {"env_step": 570000, "rew": -9.4005, "rew_std": 0.9042, "Agent": "A2C"}, {"env_step": 600000, "rew": -9.0146, "rew_std": 1.0466, "Agent": "A2C"}, {"env_step": 630000, "rew": -8.1351, "rew_std": 0.9026, "Agent": "A2C"}, {"env_step": 660000, "rew": -9.152, "rew_std": 0.8241, "Agent": "A2C"}, {"env_step": 690000, "rew": -8.4558, "rew_std": 0.9946, "Agent": "A2C"}, {"env_step": 720000, "rew": -7.3382, "rew_std": 1.0027, "Agent": "A2C"}, {"env_step": 750000, "rew": -7.5766, "rew_std": 1.0436, "Agent": "A2C"}, {"env_step": 780000, "rew": -7.7202, "rew_std": 0.8769, "Agent": "A2C"}, {"env_step": 810000, "rew": -7.1812, "rew_std": 0.9643, "Agent": "A2C"}, {"env_step": 840000, "rew": -7.4013, "rew_std": 0.8819, "Agent": "A2C"}, {"env_step": 870000, "rew": -7.1151, "rew_std": 0.3934, "Agent": "A2C"}, {"env_step": 900000, "rew": -7.1768, "rew_std": 0.9076, "Agent": "A2C"}, {"env_step": 930000, "rew": -6.7395, "rew_std": 2.2945, "Agent": "A2C"}, {"env_step": 960000, "rew": -6.9028, "rew_std": 1.674, "Agent": "A2C"}, {"env_step": 990000, "rew": -7.5811, "rew_std": 0.7885, "Agent": "A2C"}, {"env_step": 1020000, "rew": -6.0354, "rew_std": 0.527, "Agent": "A2C"}, {"env_step": 1050000, "rew": -6.4296, "rew_std": 0.9365, "Agent": "A2C"}, {"env_step": 1080000, "rew": -6.5335, "rew_std": 0.7245, "Agent": "A2C"}, {"env_step": 1110000, "rew": -6.6956, "rew_std": 1.1084, "Agent": "A2C"}, {"env_step": 1140000, "rew": -6.7058, "rew_std": 0.8603, "Agent": "A2C"}, {"env_step": 1170000, "rew": -6.4484, "rew_std": 0.6742, "Agent": "A2C"}, {"env_step": 1200000, "rew": -6.7887, "rew_std": 0.8626, "Agent": "A2C"}, {"env_step": 1230000, "rew": -7.0301, "rew_std": 0.8594, "Agent": "A2C"}, {"env_step": 1260000, "rew": -6.4574, "rew_std": 1.0401, "Agent": "A2C"}, {"env_step": 1290000, "rew": -7.4859, "rew_std": 2.1446, "Agent": "A2C"}, {"env_step": 1320000, "rew": -5.9742, "rew_std": 0.61, "Agent": "A2C"}, {"env_step": 1350000, "rew": -5.7317, "rew_std": 0.5252, "Agent": "A2C"}, {"env_step": 1380000, "rew": -5.8109, "rew_std": 0.6197, "Agent": "A2C"}, {"env_step": 1410000, "rew": -5.2524, "rew_std": 0.614, "Agent": "A2C"}, {"env_step": 1440000, "rew": -6.1422, "rew_std": 0.8794, "Agent": "A2C"}, {"env_step": 1470000, "rew": -6.0556, "rew_std": 0.5942, "Agent": "A2C"}, {"env_step": 1500000, "rew": -5.9744, "rew_std": 0.613, "Agent": "A2C"}, {"env_step": 1530000, "rew": -6.3628, "rew_std": 0.7473, "Agent": "A2C"}, {"env_step": 1560000, "rew": -6.719, "rew_std": 0.8635, "Agent": "A2C"}, {"env_step": 1590000, "rew": -6.3226, "rew_std": 0.4271, "Agent": "A2C"}, {"env_step": 1620000, "rew": -5.7314, "rew_std": 0.6983, "Agent": "A2C"}, {"env_step": 1650000, "rew": -6.3741, "rew_std": 0.6323, "Agent": "A2C"}, {"env_step": 1680000, "rew": -5.584, "rew_std": 1.0605, "Agent": "A2C"}, {"env_step": 1710000, "rew": -6.4225, "rew_std": 0.5278, "Agent": "A2C"}, {"env_step": 1740000, "rew": -5.7861, "rew_std": 0.5744, "Agent": "A2C"}, {"env_step": 1770000, "rew": -6.1038, "rew_std": 0.487, "Agent": "A2C"}, {"env_step": 1800000, "rew": -6.1468, "rew_std": 0.3817, "Agent": "A2C"}, {"env_step": 1830000, "rew": -6.3976, "rew_std": 0.4491, "Agent": "A2C"}, {"env_step": 1860000, "rew": -5.5454, "rew_std": 0.6492, "Agent": "A2C"}, {"env_step": 1890000, "rew": -5.3233, "rew_std": 0.5404, "Agent": "A2C"}, {"env_step": 1920000, "rew": -6.5189, "rew_std": 0.7128, "Agent": "A2C"}, {"env_step": 1950000, "rew": -5.5919, "rew_std": 0.7504, "Agent": "A2C"}, {"env_step": 1980000, "rew": -5.8653, "rew_std": 0.5621, "Agent": "A2C"}, {"env_step": 2010000, "rew": -6.7014, "rew_std": 0.5326, "Agent": "A2C"}, {"env_step": 2040000, "rew": -6.2351, "rew_std": 0.592, "Agent": "A2C"}, {"env_step": 2070000, "rew": -6.1591, "rew_std": 0.7988, "Agent": "A2C"}, {"env_step": 2100000, "rew": -6.4472, "rew_std": 0.6605, "Agent": "A2C"}, {"env_step": 2130000, "rew": -6.7471, "rew_std": 0.5177, "Agent": "A2C"}, {"env_step": 2160000, "rew": -5.8213, "rew_std": 0.7378, "Agent": "A2C"}, {"env_step": 2190000, "rew": -6.4161, "rew_std": 0.7222, "Agent": "A2C"}, {"env_step": 2220000, "rew": -5.8552, "rew_std": 0.5859, "Agent": "A2C"}, {"env_step": 2250000, "rew": -6.6032, "rew_std": 0.6478, "Agent": "A2C"}, {"env_step": 2280000, "rew": -6.1205, "rew_std": 0.4762, "Agent": "A2C"}, {"env_step": 2310000, "rew": -5.4231, "rew_std": 0.5739, "Agent": "A2C"}, {"env_step": 2340000, "rew": -6.4015, "rew_std": 0.7271, "Agent": "A2C"}, {"env_step": 2370000, "rew": -5.4117, "rew_std": 0.6904, "Agent": "A2C"}, {"env_step": 2400000, "rew": -6.2049, "rew_std": 0.6572, "Agent": "A2C"}, {"env_step": 2430000, "rew": -7.0885, "rew_std": 0.6712, "Agent": "A2C"}, {"env_step": 2460000, "rew": -5.7508, "rew_std": 0.7739, "Agent": "A2C"}, {"env_step": 2490000, "rew": -5.8503, "rew_std": 0.7646, "Agent": "A2C"}, {"env_step": 2520000, "rew": -6.5471, "rew_std": 0.7317, "Agent": "A2C"}, {"env_step": 2550000, "rew": -5.634, "rew_std": 0.5131, "Agent": "A2C"}, {"env_step": 2580000, "rew": -5.234, "rew_std": 0.5039, "Agent": "A2C"}, {"env_step": 2610000, "rew": -6.1475, "rew_std": 0.7397, "Agent": "A2C"}, {"env_step": 2640000, "rew": -5.426, "rew_std": 0.5692, "Agent": "A2C"}, {"env_step": 2670000, "rew": -5.9137, "rew_std": 0.9543, "Agent": "A2C"}, {"env_step": 2700000, "rew": -6.4246, "rew_std": 0.8012, "Agent": "A2C"}, {"env_step": 2730000, "rew": -5.8467, "rew_std": 0.5215, "Agent": "A2C"}, {"env_step": 2760000, "rew": -5.6174, "rew_std": 0.4854, "Agent": "A2C"}, {"env_step": 2790000, "rew": -6.5128, "rew_std": 0.5292, "Agent": "A2C"}, {"env_step": 2820000, "rew": -6.1005, "rew_std": 0.7479, "Agent": "A2C"}, {"env_step": 2850000, "rew": -5.9128, "rew_std": 0.6469, "Agent": "A2C"}, {"env_step": 2880000, "rew": -5.6554, "rew_std": 0.6749, "Agent": "A2C"}, {"env_step": 2910000, "rew": -6.1043, "rew_std": 0.508, "Agent": "A2C"}, {"env_step": 2940000, "rew": -5.8506, "rew_std": 0.6609, "Agent": "A2C"}, {"env_step": 2970000, "rew": -6.5352, "rew_std": 0.4961, "Agent": "A2C"}, {"env_step": 3000000, "rew": -6.2979, "rew_std": 0.5372, "Agent": "A2C"}, {"env_step": 0, "rew": -39.7317, "rew_std": 1.6822, "Agent": "ACKTR"}, {"env_step": 30000, "rew": -41.8399, "rew_std": 1.6702, "Agent": "ACKTR"}, {"env_step": 60000, "rew": -35.5083, "rew_std": 2.1097, "Agent": "ACKTR"}, {"env_step": 90000, "rew": -23.9253, "rew_std": 3.0823, "Agent": "ACKTR"}, {"env_step": 120000, "rew": -15.2722, "rew_std": 1.8522, "Agent": "ACKTR"}, {"env_step": 150000, "rew": -12.1623, "rew_std": 1.1907, "Agent": "ACKTR"}, {"env_step": 180000, "rew": -9.9103, "rew_std": 0.3997, "Agent": "ACKTR"}, {"env_step": 210000, "rew": -8.7393, "rew_std": 0.5881, "Agent": "ACKTR"}, {"env_step": 240000, "rew": -7.066, "rew_std": 0.3564, "Agent": "ACKTR"}, {"env_step": 270000, "rew": -7.1771, "rew_std": 0.628, "Agent": "ACKTR"}, {"env_step": 300000, "rew": -5.6094, "rew_std": 0.5681, "Agent": "ACKTR"}, {"env_step": 330000, "rew": -5.8274, "rew_std": 0.3736, "Agent": "ACKTR"}, {"env_step": 360000, "rew": -5.7496, "rew_std": 0.4386, "Agent": "ACKTR"}, {"env_step": 390000, "rew": -5.6326, "rew_std": 0.2378, "Agent": "ACKTR"}, {"env_step": 420000, "rew": -5.5348, "rew_std": 0.5618, "Agent": "ACKTR"}, {"env_step": 450000, "rew": -4.7761, "rew_std": 0.2054, "Agent": "ACKTR"}, {"env_step": 480000, "rew": -4.9062, "rew_std": 0.5271, "Agent": "ACKTR"}, {"env_step": 510000, "rew": -5.2743, "rew_std": 0.4208, "Agent": "ACKTR"}, {"env_step": 540000, "rew": -5.1959, "rew_std": 0.3448, "Agent": "ACKTR"}, {"env_step": 570000, "rew": -5.6396, "rew_std": 0.2342, "Agent": "ACKTR"}, {"env_step": 600000, "rew": -5.2343, "rew_std": 0.1805, "Agent": "ACKTR"}, {"env_step": 630000, "rew": -4.867, "rew_std": 0.4013, "Agent": "ACKTR"}, {"env_step": 660000, "rew": -5.4243, "rew_std": 0.3806, "Agent": "ACKTR"}, {"env_step": 690000, "rew": -4.812, "rew_std": 0.2571, "Agent": "ACKTR"}, {"env_step": 720000, "rew": -4.3747, "rew_std": 0.1226, "Agent": "ACKTR"}, {"env_step": 750000, "rew": -4.6524, "rew_std": 0.2749, "Agent": "ACKTR"}, {"env_step": 780000, "rew": -4.7926, "rew_std": 0.2872, "Agent": "ACKTR"}, {"env_step": 810000, "rew": -4.6667, "rew_std": 0.3082, "Agent": "ACKTR"}, {"env_step": 840000, "rew": -4.8452, "rew_std": 0.3639, "Agent": "ACKTR"}, {"env_step": 870000, "rew": -4.3715, "rew_std": 0.3478, "Agent": "ACKTR"}, {"env_step": 900000, "rew": -4.586, "rew_std": 0.3333, "Agent": "ACKTR"}, {"env_step": 930000, "rew": -3.8109, "rew_std": 0.28, "Agent": "ACKTR"}, {"env_step": 960000, "rew": -4.305, "rew_std": 0.3777, "Agent": "ACKTR"}, {"env_step": 990000, "rew": -4.6298, "rew_std": 0.5107, "Agent": "ACKTR"}, {"env_step": 1020000, "rew": -4.033, "rew_std": 0.2415, "Agent": "ACKTR"}, {"env_step": 1050000, "rew": -4.3536, "rew_std": 0.2648, "Agent": "ACKTR"}, {"env_step": 1080000, "rew": -4.3902, "rew_std": 0.193, "Agent": "ACKTR"}, {"env_step": 1110000, "rew": -4.5671, "rew_std": 0.3135, "Agent": "ACKTR"}, {"env_step": 1140000, "rew": -4.4315, "rew_std": 0.1741, "Agent": "ACKTR"}, {"env_step": 1170000, "rew": -4.2451, "rew_std": 0.1843, "Agent": "ACKTR"}, {"env_step": 1200000, "rew": -4.6325, "rew_std": 0.315, "Agent": "ACKTR"}, {"env_step": 1230000, "rew": -4.7223, "rew_std": 0.2351, "Agent": "ACKTR"}, {"env_step": 1260000, "rew": -4.44, "rew_std": 0.1657, "Agent": "ACKTR"}, {"env_step": 1290000, "rew": -4.9958, "rew_std": 0.4753, "Agent": "ACKTR"}, {"env_step": 1320000, "rew": -4.293, "rew_std": 0.4098, "Agent": "ACKTR"}, {"env_step": 1350000, "rew": -4.0946, "rew_std": 0.1995, "Agent": "ACKTR"}, {"env_step": 1380000, "rew": -4.1148, "rew_std": 0.4162, "Agent": "ACKTR"}, {"env_step": 1410000, "rew": -3.605, "rew_std": 0.2686, "Agent": "ACKTR"}, {"env_step": 1440000, "rew": -4.4264, "rew_std": 0.5546, "Agent": "ACKTR"}, {"env_step": 1470000, "rew": -4.2569, "rew_std": 0.2736, "Agent": "ACKTR"}, {"env_step": 1500000, "rew": -4.0596, "rew_std": 0.2016, "Agent": "ACKTR"}, {"env_step": 1530000, "rew": -4.4355, "rew_std": 0.4763, "Agent": "ACKTR"}, {"env_step": 1560000, "rew": -4.5804, "rew_std": 0.2757, "Agent": "ACKTR"}, {"env_step": 1590000, "rew": -4.3835, "rew_std": 0.232, "Agent": "ACKTR"}, {"env_step": 1620000, "rew": -4.0913, "rew_std": 0.3999, "Agent": "ACKTR"}, {"env_step": 1650000, "rew": -4.4874, "rew_std": 0.2044, "Agent": "ACKTR"}, {"env_step": 1680000, "rew": -3.8345, "rew_std": 0.5302, "Agent": "ACKTR"}, {"env_step": 1710000, "rew": -4.4205, "rew_std": 0.1666, "Agent": "ACKTR"}, {"env_step": 1740000, "rew": -3.928, "rew_std": 0.1601, "Agent": "ACKTR"}, {"env_step": 1770000, "rew": -4.3831, "rew_std": 0.307, "Agent": "ACKTR"}, {"env_step": 1800000, "rew": -4.2658, "rew_std": 0.2749, "Agent": "ACKTR"}, {"env_step": 1830000, "rew": -4.3866, "rew_std": 0.1768, "Agent": "ACKTR"}, {"env_step": 1860000, "rew": -3.8961, "rew_std": 0.2482, "Agent": "ACKTR"}, {"env_step": 1890000, "rew": -3.8917, "rew_std": 0.4286, "Agent": "ACKTR"}, {"env_step": 1920000, "rew": -4.5475, "rew_std": 0.3182, "Agent": "ACKTR"}, {"env_step": 1950000, "rew": -3.8164, "rew_std": 0.2863, "Agent": "ACKTR"}, {"env_step": 1980000, "rew": -4.2562, "rew_std": 0.3606, "Agent": "ACKTR"}, {"env_step": 2010000, "rew": -4.8628, "rew_std": 0.4978, "Agent": "ACKTR"}, {"env_step": 2040000, "rew": -4.5695, "rew_std": 0.4109, "Agent": "ACKTR"}, {"env_step": 2070000, "rew": -4.5813, "rew_std": 0.3069, "Agent": "ACKTR"}, {"env_step": 2100000, "rew": -4.8193, "rew_std": 0.2102, "Agent": "ACKTR"}, {"env_step": 2130000, "rew": -5.3441, "rew_std": 0.7474, "Agent": "ACKTR"}, {"env_step": 2160000, "rew": -4.0601, "rew_std": 0.304, "Agent": "ACKTR"}, {"env_step": 2190000, "rew": -5.0169, "rew_std": 0.5489, "Agent": "ACKTR"}, {"env_step": 2220000, "rew": -4.3338, "rew_std": 0.3029, "Agent": "ACKTR"}, {"env_step": 2250000, "rew": -4.9522, "rew_std": 0.3546, "Agent": "ACKTR"}, {"env_step": 2280000, "rew": -4.4238, "rew_std": 0.2798, "Agent": "ACKTR"}, {"env_step": 2310000, "rew": -3.8948, "rew_std": 0.3034, "Agent": "ACKTR"}, {"env_step": 2340000, "rew": -4.7082, "rew_std": 0.2701, "Agent": "ACKTR"}, {"env_step": 2370000, "rew": -3.8277, "rew_std": 0.2334, "Agent": "ACKTR"}, {"env_step": 2400000, "rew": -4.5462, "rew_std": 0.2392, "Agent": "ACKTR"}, {"env_step": 2430000, "rew": -5.4222, "rew_std": 0.4012, "Agent": "ACKTR"}, {"env_step": 2460000, "rew": -4.2217, "rew_std": 0.2306, "Agent": "ACKTR"}, {"env_step": 2490000, "rew": -4.1957, "rew_std": 0.5324, "Agent": "ACKTR"}, {"env_step": 2520000, "rew": -4.7113, "rew_std": 0.2886, "Agent": "ACKTR"}, {"env_step": 2550000, "rew": -4.2321, "rew_std": 0.3292, "Agent": "ACKTR"}, {"env_step": 2580000, "rew": -3.8531, "rew_std": 0.2832, "Agent": "ACKTR"}, {"env_step": 2610000, "rew": -4.5437, "rew_std": 0.3004, "Agent": "ACKTR"}, {"env_step": 2640000, "rew": -4.0963, "rew_std": 0.3203, "Agent": "ACKTR"}, {"env_step": 2670000, "rew": -4.269, "rew_std": 0.4699, "Agent": "ACKTR"}, {"env_step": 2700000, "rew": -4.639, "rew_std": 0.3858, "Agent": "ACKTR"}, {"env_step": 2730000, "rew": -4.4194, "rew_std": 0.3559, "Agent": "ACKTR"}, {"env_step": 2760000, "rew": -4.2282, "rew_std": 0.2393, "Agent": "ACKTR"}, {"env_step": 2790000, "rew": -5.0154, "rew_std": 0.3349, "Agent": "ACKTR"}, {"env_step": 2820000, "rew": -4.3347, "rew_std": 0.139, "Agent": "ACKTR"}, {"env_step": 2850000, "rew": -4.4802, "rew_std": 0.2004, "Agent": "ACKTR"}, {"env_step": 2880000, "rew": -4.2491, "rew_std": 0.1211, "Agent": "ACKTR"}, {"env_step": 2910000, "rew": -4.6821, "rew_std": 0.161, "Agent": "ACKTR"}, {"env_step": 2940000, "rew": -4.3028, "rew_std": 0.2901, "Agent": "ACKTR"}, {"env_step": 2970000, "rew": -5.068, "rew_std": 0.4142, "Agent": "ACKTR"}, {"env_step": 3000000, "rew": -4.8591, "rew_std": 0.2661, "Agent": "ACKTR"}, {"env_step": 0, "rew": -27.3232, "rew_std": 23.4601, "Agent": "DDPG"}, {"env_step": 5000, "rew": -5.9994, "rew_std": 0.4863, "Agent": "DDPG"}, {"env_step": 10000, "rew": -5.9481, "rew_std": 0.5947, "Agent": "DDPG"}, {"env_step": 15000, "rew": -6.5493, "rew_std": 0.871, "Agent": "DDPG"}, {"env_step": 20000, "rew": -5.3363, "rew_std": 0.6571, "Agent": "DDPG"}, {"env_step": 25000, "rew": -6.3717, "rew_std": 0.7762, "Agent": "DDPG"}, {"env_step": 30000, "rew": -5.3757, "rew_std": 0.4863, "Agent": "DDPG"}, {"env_step": 35000, "rew": -5.3225, "rew_std": 0.3755, "Agent": "DDPG"}, {"env_step": 40000, "rew": -5.1545, "rew_std": 0.2959, "Agent": "DDPG"}, {"env_step": 45000, "rew": -5.1735, "rew_std": 0.5609, "Agent": "DDPG"}, {"env_step": 50000, "rew": -5.0773, "rew_std": 0.3339, "Agent": "DDPG"}, {"env_step": 55000, "rew": -5.1035, "rew_std": 0.3217, "Agent": "DDPG"}, {"env_step": 60000, "rew": -4.4369, "rew_std": 0.3355, "Agent": "DDPG"}, {"env_step": 65000, "rew": -4.1462, "rew_std": 0.2317, "Agent": "DDPG"}, {"env_step": 70000, "rew": -4.7954, "rew_std": 0.4211, "Agent": "DDPG"}, {"env_step": 75000, "rew": -4.3913, "rew_std": 0.1985, "Agent": "DDPG"}, {"env_step": 80000, "rew": -4.5597, "rew_std": 0.2783, "Agent": "DDPG"}, {"env_step": 85000, "rew": -4.3348, "rew_std": 0.2622, "Agent": "DDPG"}, {"env_step": 90000, "rew": -5.0381, "rew_std": 0.4593, "Agent": "DDPG"}, {"env_step": 95000, "rew": -4.6645, "rew_std": 0.3458, "Agent": "DDPG"}, {"env_step": 100000, "rew": -4.5549, "rew_std": 0.188, "Agent": "DDPG"}, {"env_step": 105000, "rew": -4.6647, "rew_std": 0.182, "Agent": "DDPG"}, {"env_step": 110000, "rew": -4.8689, "rew_std": 0.2584, "Agent": "DDPG"}, {"env_step": 115000, "rew": -4.1283, "rew_std": 0.1862, "Agent": "DDPG"}, {"env_step": 120000, "rew": -3.6985, "rew_std": 0.2483, "Agent": "DDPG"}, {"env_step": 125000, "rew": -3.8125, "rew_std": 0.2723, "Agent": "DDPG"}, {"env_step": 130000, "rew": -4.3951, "rew_std": 0.2996, "Agent": "DDPG"}, {"env_step": 135000, "rew": -4.2906, "rew_std": 0.4147, "Agent": "DDPG"}, {"env_step": 140000, "rew": -4.4004, "rew_std": 0.3321, "Agent": "DDPG"}, {"env_step": 145000, "rew": -4.9837, "rew_std": 0.3403, "Agent": "DDPG"}, {"env_step": 150000, "rew": -4.4368, "rew_std": 0.2152, "Agent": "DDPG"}, {"env_step": 155000, "rew": -4.2693, "rew_std": 0.4226, "Agent": "DDPG"}, {"env_step": 160000, "rew": -4.2912, "rew_std": 0.2346, "Agent": "DDPG"}, {"env_step": 165000, "rew": -4.357, "rew_std": 0.3799, "Agent": "DDPG"}, {"env_step": 170000, "rew": -4.3997, "rew_std": 0.2363, "Agent": "DDPG"}, {"env_step": 175000, "rew": -4.3367, "rew_std": 0.1632, "Agent": "DDPG"}, {"env_step": 180000, "rew": -4.3578, "rew_std": 0.1974, "Agent": "DDPG"}, {"env_step": 185000, "rew": -3.8391, "rew_std": 0.2901, "Agent": "DDPG"}, {"env_step": 190000, "rew": -4.132, "rew_std": 0.2211, "Agent": "DDPG"}, {"env_step": 195000, "rew": -3.8273, "rew_std": 0.2488, "Agent": "DDPG"}, {"env_step": 200000, "rew": -3.7421, "rew_std": 0.2776, "Agent": "DDPG"}, {"env_step": 205000, "rew": -4.2475, "rew_std": 0.2108, "Agent": "DDPG"}, {"env_step": 210000, "rew": -4.4562, "rew_std": 0.1796, "Agent": "DDPG"}, {"env_step": 215000, "rew": -4.5319, "rew_std": 0.2057, "Agent": "DDPG"}, {"env_step": 220000, "rew": -3.9499, "rew_std": 0.3337, "Agent": "DDPG"}, {"env_step": 225000, "rew": -4.3857, "rew_std": 0.1958, "Agent": "DDPG"}, {"env_step": 230000, "rew": -4.2473, "rew_std": 0.1687, "Agent": "DDPG"}, {"env_step": 235000, "rew": -3.4639, "rew_std": 0.26, "Agent": "DDPG"}, {"env_step": 240000, "rew": -4.5433, "rew_std": 0.2626, "Agent": "DDPG"}, {"env_step": 245000, "rew": -4.3408, "rew_std": 0.2718, "Agent": "DDPG"}, {"env_step": 250000, "rew": -4.1629, "rew_std": 0.2863, "Agent": "DDPG"}, {"env_step": 255000, "rew": -3.6422, "rew_std": 0.3542, "Agent": "DDPG"}, {"env_step": 260000, "rew": -4.1054, "rew_std": 0.1149, "Agent": "DDPG"}, {"env_step": 265000, "rew": -3.9174, "rew_std": 0.2286, "Agent": "DDPG"}, {"env_step": 270000, "rew": -4.0504, "rew_std": 0.2778, "Agent": "DDPG"}, {"env_step": 275000, "rew": -4.0093, "rew_std": 0.24, "Agent": "DDPG"}, {"env_step": 280000, "rew": -4.1029, "rew_std": 0.2496, "Agent": "DDPG"}, {"env_step": 285000, "rew": -4.492, "rew_std": 0.2369, "Agent": "DDPG"}, {"env_step": 290000, "rew": -3.8098, "rew_std": 0.1355, "Agent": "DDPG"}, {"env_step": 295000, "rew": -3.905, "rew_std": 0.1612, "Agent": "DDPG"}, {"env_step": 300000, "rew": -4.1215, "rew_std": 0.5278, "Agent": "DDPG"}, {"env_step": 305000, "rew": -4.007, "rew_std": 0.1152, "Agent": "DDPG"}, {"env_step": 310000, "rew": -4.3045, "rew_std": 0.1947, "Agent": "DDPG"}, {"env_step": 315000, "rew": -4.2704, "rew_std": 0.1864, "Agent": "DDPG"}, {"env_step": 320000, "rew": -3.6252, "rew_std": 0.27, "Agent": "DDPG"}, {"env_step": 325000, "rew": -4.5046, "rew_std": 0.3124, "Agent": "DDPG"}, {"env_step": 330000, "rew": -4.3069, "rew_std": 0.2592, "Agent": "DDPG"}, {"env_step": 335000, "rew": -3.7179, "rew_std": 0.3197, "Agent": "DDPG"}, {"env_step": 340000, "rew": -3.7661, "rew_std": 0.2643, "Agent": "DDPG"}, {"env_step": 345000, "rew": -4.0593, "rew_std": 0.2877, "Agent": "DDPG"}, {"env_step": 350000, "rew": -4.0207, "rew_std": 0.2279, "Agent": "DDPG"}, {"env_step": 355000, "rew": -3.2942, "rew_std": 0.2682, "Agent": "DDPG"}, {"env_step": 360000, "rew": -3.8581, "rew_std": 0.3476, "Agent": "DDPG"}, {"env_step": 365000, "rew": -4.7662, "rew_std": 0.2355, "Agent": "DDPG"}, {"env_step": 370000, "rew": -3.8946, "rew_std": 0.3209, "Agent": "DDPG"}, {"env_step": 375000, "rew": -4.2492, "rew_std": 0.2504, "Agent": "DDPG"}, {"env_step": 380000, "rew": -4.3849, "rew_std": 0.2134, "Agent": "DDPG"}, {"env_step": 385000, "rew": -4.0957, "rew_std": 0.4477, "Agent": "DDPG"}, {"env_step": 390000, "rew": -4.9408, "rew_std": 0.1723, "Agent": "DDPG"}, {"env_step": 395000, "rew": -4.0376, "rew_std": 0.3935, "Agent": "DDPG"}, {"env_step": 400000, "rew": -4.0078, "rew_std": 0.1518, "Agent": "DDPG"}, {"env_step": 405000, "rew": -4.3918, "rew_std": 0.301, "Agent": "DDPG"}, {"env_step": 410000, "rew": -4.2993, "rew_std": 0.1881, "Agent": "DDPG"}, {"env_step": 415000, "rew": -4.065, "rew_std": 0.2356, "Agent": "DDPG"}, {"env_step": 420000, "rew": -4.284, "rew_std": 0.2906, "Agent": "DDPG"}, {"env_step": 425000, "rew": -4.431, "rew_std": 0.1105, "Agent": "DDPG"}, {"env_step": 430000, "rew": -4.2572, "rew_std": 0.3112, "Agent": "DDPG"}, {"env_step": 435000, "rew": -4.4992, "rew_std": 0.2926, "Agent": "DDPG"}, {"env_step": 440000, "rew": -4.4105, "rew_std": 0.3677, "Agent": "DDPG"}, {"env_step": 445000, "rew": -4.1118, "rew_std": 0.3003, "Agent": "DDPG"}, {"env_step": 450000, "rew": -4.1832, "rew_std": 0.3488, "Agent": "DDPG"}, {"env_step": 455000, "rew": -3.6541, "rew_std": 0.3019, "Agent": "DDPG"}, {"env_step": 460000, "rew": -4.1346, "rew_std": 0.192, "Agent": "DDPG"}, {"env_step": 465000, "rew": -4.4254, "rew_std": 0.3568, "Agent": "DDPG"}, {"env_step": 470000, "rew": -3.9608, "rew_std": 0.2456, "Agent": "DDPG"}, {"env_step": 475000, "rew": -3.8078, "rew_std": 0.6135, "Agent": "DDPG"}, {"env_step": 480000, "rew": -4.3577, "rew_std": 0.2294, "Agent": "DDPG"}, {"env_step": 485000, "rew": -4.2809, "rew_std": 0.2382, "Agent": "DDPG"}, {"env_step": 490000, "rew": -3.5478, "rew_std": 0.3021, "Agent": "DDPG"}, {"env_step": 495000, "rew": -4.309, "rew_std": 0.419, "Agent": "DDPG"}, {"env_step": 500000, "rew": -4.184, "rew_std": 0.1899, "Agent": "DDPG"}, {"env_step": 505000, "rew": -4.6083, "rew_std": 0.4478, "Agent": "DDPG"}, {"env_step": 510000, "rew": -4.193, "rew_std": 0.4263, "Agent": "DDPG"}, {"env_step": 515000, "rew": -4.4484, "rew_std": 0.6183, "Agent": "DDPG"}, {"env_step": 520000, "rew": -4.5897, "rew_std": 0.3247, "Agent": "DDPG"}, {"env_step": 525000, "rew": -4.3144, "rew_std": 0.4962, "Agent": "DDPG"}, {"env_step": 530000, "rew": -3.7567, "rew_std": 0.3392, "Agent": "DDPG"}, {"env_step": 535000, "rew": -4.8428, "rew_std": 0.2237, "Agent": "DDPG"}, {"env_step": 540000, "rew": -4.0561, "rew_std": 0.3695, "Agent": "DDPG"}, {"env_step": 545000, "rew": -3.7848, "rew_std": 0.3187, "Agent": "DDPG"}, {"env_step": 550000, "rew": -4.7356, "rew_std": 0.3935, "Agent": "DDPG"}, {"env_step": 555000, "rew": -4.3297, "rew_std": 0.2376, "Agent": "DDPG"}, {"env_step": 560000, "rew": -3.7468, "rew_std": 0.132, "Agent": "DDPG"}, {"env_step": 565000, "rew": -4.7899, "rew_std": 0.2909, "Agent": "DDPG"}, {"env_step": 570000, "rew": -3.826, "rew_std": 0.2805, "Agent": "DDPG"}, {"env_step": 575000, "rew": -4.3571, "rew_std": 0.3701, "Agent": "DDPG"}, {"env_step": 580000, "rew": -3.8213, "rew_std": 0.2697, "Agent": "DDPG"}, {"env_step": 585000, "rew": -3.8807, "rew_std": 0.577, "Agent": "DDPG"}, {"env_step": 590000, "rew": -3.7687, "rew_std": 0.2783, "Agent": "DDPG"}, {"env_step": 595000, "rew": -3.8111, "rew_std": 0.2123, "Agent": "DDPG"}, {"env_step": 600000, "rew": -4.4374, "rew_std": 0.2168, "Agent": "DDPG"}, {"env_step": 605000, "rew": -4.4213, "rew_std": 0.3345, "Agent": "DDPG"}, {"env_step": 610000, "rew": -5.3496, "rew_std": 0.1879, "Agent": "DDPG"}, {"env_step": 615000, "rew": -4.6118, "rew_std": 0.4872, "Agent": "DDPG"}, {"env_step": 620000, "rew": -5.0175, "rew_std": 0.3868, "Agent": "DDPG"}, {"env_step": 625000, "rew": -4.2684, "rew_std": 0.4877, "Agent": "DDPG"}, {"env_step": 630000, "rew": -4.2208, "rew_std": 0.5298, "Agent": "DDPG"}, {"env_step": 635000, "rew": -4.0813, "rew_std": 0.341, "Agent": "DDPG"}, {"env_step": 640000, "rew": -4.1259, "rew_std": 0.2516, "Agent": "DDPG"}, {"env_step": 645000, "rew": -4.3379, "rew_std": 0.1992, "Agent": "DDPG"}, {"env_step": 650000, "rew": -3.7851, "rew_std": 0.3134, "Agent": "DDPG"}, {"env_step": 655000, "rew": -4.5744, "rew_std": 0.4368, "Agent": "DDPG"}, {"env_step": 660000, "rew": -4.7546, "rew_std": 0.121, "Agent": "DDPG"}, {"env_step": 665000, "rew": -4.6352, "rew_std": 0.3387, "Agent": "DDPG"}, {"env_step": 670000, "rew": -4.0116, "rew_std": 0.4186, "Agent": "DDPG"}, {"env_step": 675000, "rew": -4.2434, "rew_std": 0.2248, "Agent": "DDPG"}, {"env_step": 680000, "rew": -4.0583, "rew_std": 0.4662, "Agent": "DDPG"}, {"env_step": 685000, "rew": -4.6387, "rew_std": 0.6938, "Agent": "DDPG"}, {"env_step": 690000, "rew": -3.9708, "rew_std": 0.345, "Agent": "DDPG"}, {"env_step": 695000, "rew": -4.3476, "rew_std": 0.3352, "Agent": "DDPG"}, {"env_step": 700000, "rew": -4.8799, "rew_std": 0.2911, "Agent": "DDPG"}, {"env_step": 705000, "rew": -3.6108, "rew_std": 0.826, "Agent": "DDPG"}, {"env_step": 710000, "rew": -4.6422, "rew_std": 0.2948, "Agent": "DDPG"}, {"env_step": 715000, "rew": -4.4962, "rew_std": 0.3051, "Agent": "DDPG"}, {"env_step": 720000, "rew": -4.9724, "rew_std": 0.3331, "Agent": "DDPG"}, {"env_step": 725000, "rew": -4.9428, "rew_std": 0.402, "Agent": "DDPG"}, {"env_step": 730000, "rew": -4.8311, "rew_std": 0.3027, "Agent": "DDPG"}, {"env_step": 735000, "rew": -4.9349, "rew_std": 0.4743, "Agent": "DDPG"}, {"env_step": 740000, "rew": -4.1416, "rew_std": 0.3314, "Agent": "DDPG"}, {"env_step": 745000, "rew": -5.0792, "rew_std": 0.396, "Agent": "DDPG"}, {"env_step": 750000, "rew": -4.3809, "rew_std": 0.3205, "Agent": "DDPG"}, {"env_step": 755000, "rew": -4.7253, "rew_std": 0.3842, "Agent": "DDPG"}, {"env_step": 760000, "rew": -4.9929, "rew_std": 0.4151, "Agent": "DDPG"}, {"env_step": 765000, "rew": -4.7099, "rew_std": 0.5626, "Agent": "DDPG"}, {"env_step": 770000, "rew": -4.4012, "rew_std": 0.3591, "Agent": "DDPG"}, {"env_step": 775000, "rew": -3.8417, "rew_std": 0.3934, "Agent": "DDPG"}, {"env_step": 780000, "rew": -3.9774, "rew_std": 0.2247, "Agent": "DDPG"}, {"env_step": 785000, "rew": -4.5148, "rew_std": 0.4076, "Agent": "DDPG"}, {"env_step": 790000, "rew": -4.4641, "rew_std": 0.244, "Agent": "DDPG"}, {"env_step": 795000, "rew": -5.0113, "rew_std": 0.4511, "Agent": "DDPG"}, {"env_step": 800000, "rew": -4.7334, "rew_std": 0.2928, "Agent": "DDPG"}, {"env_step": 805000, "rew": -4.5561, "rew_std": 0.2719, "Agent": "DDPG"}, {"env_step": 810000, "rew": -4.6724, "rew_std": 0.2335, "Agent": "DDPG"}, {"env_step": 815000, "rew": -4.3218, "rew_std": 0.2871, "Agent": "DDPG"}, {"env_step": 820000, "rew": -5.0469, "rew_std": 0.4414, "Agent": "DDPG"}, {"env_step": 825000, "rew": -4.653, "rew_std": 0.4338, "Agent": "DDPG"}, {"env_step": 830000, "rew": -4.8143, "rew_std": 0.525, "Agent": "DDPG"}, {"env_step": 835000, "rew": -4.8063, "rew_std": 0.3875, "Agent": "DDPG"}, {"env_step": 840000, "rew": -4.106, "rew_std": 0.2461, "Agent": "DDPG"}, {"env_step": 845000, "rew": -4.5475, "rew_std": 0.2879, "Agent": "DDPG"}, {"env_step": 850000, "rew": -4.7167, "rew_std": 0.5187, "Agent": "DDPG"}, {"env_step": 855000, "rew": -4.6854, "rew_std": 0.2957, "Agent": "DDPG"}, {"env_step": 860000, "rew": -4.3747, "rew_std": 0.2721, "Agent": "DDPG"}, {"env_step": 865000, "rew": -4.4879, "rew_std": 0.3751, "Agent": "DDPG"}, {"env_step": 870000, "rew": -4.8097, "rew_std": 0.1644, "Agent": "DDPG"}, {"env_step": 875000, "rew": -4.1463, "rew_std": 0.3703, "Agent": "DDPG"}, {"env_step": 880000, "rew": -4.6397, "rew_std": 0.4628, "Agent": "DDPG"}, {"env_step": 885000, "rew": -4.554, "rew_std": 0.2611, "Agent": "DDPG"}, {"env_step": 890000, "rew": -4.0128, "rew_std": 0.3459, "Agent": "DDPG"}, {"env_step": 895000, "rew": -4.3408, "rew_std": 0.5245, "Agent": "DDPG"}, {"env_step": 900000, "rew": -3.8282, "rew_std": 0.2118, "Agent": "DDPG"}, {"env_step": 905000, "rew": -5.5158, "rew_std": 0.5981, "Agent": "DDPG"}, {"env_step": 910000, "rew": -4.8566, "rew_std": 0.4799, "Agent": "DDPG"}, {"env_step": 915000, "rew": -4.8133, "rew_std": 0.3469, "Agent": "DDPG"}, {"env_step": 920000, "rew": -5.049, "rew_std": 0.5046, "Agent": "DDPG"}, {"env_step": 925000, "rew": -4.2925, "rew_std": 0.3937, "Agent": "DDPG"}, {"env_step": 930000, "rew": -4.9669, "rew_std": 0.417, "Agent": "DDPG"}, {"env_step": 935000, "rew": -5.1534, "rew_std": 0.7335, "Agent": "DDPG"}, {"env_step": 940000, "rew": -5.2228, "rew_std": 0.6543, "Agent": "DDPG"}, {"env_step": 945000, "rew": -4.6248, "rew_std": 0.6695, "Agent": "DDPG"}, {"env_step": 950000, "rew": -4.8075, "rew_std": 0.5397, "Agent": "DDPG"}, {"env_step": 955000, "rew": -4.5568, "rew_std": 0.4897, "Agent": "DDPG"}, {"env_step": 960000, "rew": -4.7383, "rew_std": 1.3685, "Agent": "DDPG"}, {"env_step": 965000, "rew": -4.9158, "rew_std": 0.7738, "Agent": "DDPG"}, {"env_step": 970000, "rew": -5.361, "rew_std": 0.4219, "Agent": "DDPG"}, {"env_step": 975000, "rew": -5.0993, "rew_std": 0.5179, "Agent": "DDPG"}, {"env_step": 980000, "rew": -5.2621, "rew_std": 0.5666, "Agent": "DDPG"}, {"env_step": 985000, "rew": -4.7954, "rew_std": 0.6463, "Agent": "DDPG"}, {"env_step": 990000, "rew": -4.0475, "rew_std": 0.4556, "Agent": "DDPG"}, {"env_step": 995000, "rew": -4.261, "rew_std": 0.3856, "Agent": "DDPG"}, {"env_step": 1000000, "rew": -5.1163, "rew_std": 0.4632, "Agent": "DDPG"}, {"env_step": 1005000, "rew": -5.6486, "rew_std": 1.3292, "Agent": "DDPG"}, {"env_step": 1010000, "rew": -5.588, "rew_std": 1.9266, "Agent": "DDPG"}, {"env_step": 1015000, "rew": -7.7173, "rew_std": 3.5321, "Agent": "DDPG"}, {"env_step": 1020000, "rew": -7.9336, "rew_std": 3.2407, "Agent": "DDPG"}, {"env_step": 1025000, "rew": -9.0305, "rew_std": 4.5181, "Agent": "DDPG"}, {"env_step": 1030000, "rew": -11.4767, "rew_std": 8.7641, "Agent": "DDPG"}, {"env_step": 1035000, "rew": -9.7738, "rew_std": 6.5195, "Agent": "DDPG"}, {"env_step": 1040000, "rew": -10.5483, "rew_std": 7.6541, "Agent": "DDPG"}, {"env_step": 1045000, "rew": -13.2258, "rew_std": 15.421, "Agent": "DDPG"}, {"env_step": 1050000, "rew": -20.784, "rew_std": 23.1296, "Agent": "DDPG"}, {"env_step": 1055000, "rew": -18.1494, "rew_std": 20.8153, "Agent": "DDPG"}, {"env_step": 1060000, "rew": -20.7918, "rew_std": 27.238, "Agent": "DDPG"}, {"env_step": 1065000, "rew": -14.8026, "rew_std": 12.7541, "Agent": "DDPG"}, {"env_step": 1070000, "rew": -19.7576, "rew_std": 22.8814, "Agent": "DDPG"}, {"env_step": 1075000, "rew": -15.4066, "rew_std": 12.2726, "Agent": "DDPG"}, {"env_step": 1080000, "rew": -12.5202, "rew_std": 7.5183, "Agent": "DDPG"}, {"env_step": 1085000, "rew": -20.5579, "rew_std": 17.4525, "Agent": "DDPG"}, {"env_step": 1090000, "rew": -14.0937, "rew_std": 11.4289, "Agent": "DDPG"}, {"env_step": 1095000, "rew": -15.7974, "rew_std": 12.7581, "Agent": "DDPG"}, {"env_step": 1100000, "rew": -15.1148, "rew_std": 10.7843, "Agent": "DDPG"}, {"env_step": 1105000, "rew": -16.2613, "rew_std": 12.6272, "Agent": "DDPG"}, {"env_step": 1110000, "rew": -17.2591, "rew_std": 15.419, "Agent": "DDPG"}, {"env_step": 1115000, "rew": -19.0267, "rew_std": 15.5475, "Agent": "DDPG"}, {"env_step": 1120000, "rew": -22.7455, "rew_std": 17.976, "Agent": "DDPG"}, {"env_step": 1125000, "rew": -18.2955, "rew_std": 14.3416, "Agent": "DDPG"}, {"env_step": 1130000, "rew": -20.4421, "rew_std": 11.4797, "Agent": "DDPG"}, {"env_step": 1135000, "rew": -15.9736, "rew_std": 6.5837, "Agent": "DDPG"}, {"env_step": 1140000, "rew": -19.6391, "rew_std": 13.1862, "Agent": "DDPG"}, {"env_step": 1145000, "rew": -23.2974, "rew_std": 13.0105, "Agent": "DDPG"}, {"env_step": 1150000, "rew": -21.9923, "rew_std": 11.1915, "Agent": "DDPG"}, {"env_step": 1155000, "rew": -25.8502, "rew_std": 14.6756, "Agent": "DDPG"}, {"env_step": 1160000, "rew": -26.8855, "rew_std": 18.5184, "Agent": "DDPG"}, {"env_step": 1165000, "rew": -22.6703, "rew_std": 11.9136, "Agent": "DDPG"}, {"env_step": 1170000, "rew": -25.7278, "rew_std": 11.4867, "Agent": "DDPG"}, {"env_step": 1175000, "rew": -18.4098, "rew_std": 8.5134, "Agent": "DDPG"}, {"env_step": 1180000, "rew": -25.0163, "rew_std": 14.2717, "Agent": "DDPG"}, {"env_step": 1185000, "rew": -17.7322, "rew_std": 9.6582, "Agent": "DDPG"}, {"env_step": 1190000, "rew": -20.5272, "rew_std": 12.0385, "Agent": "DDPG"}, {"env_step": 1195000, "rew": -25.2786, "rew_std": 23.9859, "Agent": "DDPG"}, {"env_step": 1200000, "rew": -29.8174, "rew_std": 32.2052, "Agent": "DDPG"}, {"env_step": 1205000, "rew": -22.3033, "rew_std": 18.2211, "Agent": "DDPG"}, {"env_step": 1210000, "rew": -18.0601, "rew_std": 6.9453, "Agent": "DDPG"}, {"env_step": 1215000, "rew": -16.9678, "rew_std": 9.2312, "Agent": "DDPG"}, {"env_step": 1220000, "rew": -15.8163, "rew_std": 10.0092, "Agent": "DDPG"}, {"env_step": 1225000, "rew": -14.2974, "rew_std": 9.1534, "Agent": "DDPG"}, {"env_step": 1230000, "rew": -13.7051, "rew_std": 8.1698, "Agent": "DDPG"}, {"env_step": 1235000, "rew": -12.1851, "rew_std": 7.4597, "Agent": "DDPG"}, {"env_step": 1240000, "rew": -10.4908, "rew_std": 6.1628, "Agent": "DDPG"}, {"env_step": 1245000, "rew": -12.2744, "rew_std": 9.3555, "Agent": "DDPG"}, {"env_step": 1250000, "rew": -10.4825, "rew_std": 4.1534, "Agent": "DDPG"}, {"env_step": 0, "rew": -39.7236, "rew_std": 1.6682, "Agent": "NPG"}, {"env_step": 30720, "rew": -38.0815, "rew_std": 0.8891, "Agent": "NPG"}, {"env_step": 61440, "rew": -32.876, "rew_std": 1.8294, "Agent": "NPG"}, {"env_step": 92160, "rew": -26.1409, "rew_std": 2.6639, "Agent": "NPG"}, {"env_step": 122880, "rew": -18.7563, "rew_std": 1.6028, "Agent": "NPG"}, {"env_step": 153600, "rew": -13.9997, "rew_std": 1.4414, "Agent": "NPG"}, {"env_step": 184320, "rew": -12.1748, "rew_std": 1.0175, "Agent": "NPG"}, {"env_step": 215040, "rew": -10.5119, "rew_std": 0.9977, "Agent": "NPG"}, {"env_step": 245760, "rew": -9.4138, "rew_std": 0.7466, "Agent": "NPG"}, {"env_step": 276480, "rew": -9.1172, "rew_std": 1.0264, "Agent": "NPG"}, {"env_step": 307200, "rew": -7.6342, "rew_std": 0.6116, "Agent": "NPG"}, {"env_step": 337920, "rew": -7.959, "rew_std": 0.7169, "Agent": "NPG"}, {"env_step": 368640, "rew": -8.3696, "rew_std": 0.9109, "Agent": "NPG"}, {"env_step": 399360, "rew": -7.1806, "rew_std": 0.8393, "Agent": "NPG"}, {"env_step": 430080, "rew": -7.3921, "rew_std": 0.7765, "Agent": "NPG"}, {"env_step": 460800, "rew": -6.2652, "rew_std": 0.516, "Agent": "NPG"}, {"env_step": 491520, "rew": -6.5527, "rew_std": 0.8613, "Agent": "NPG"}, {"env_step": 522240, "rew": -7.0629, "rew_std": 0.8388, "Agent": "NPG"}, {"env_step": 552960, "rew": -6.9348, "rew_std": 0.8159, "Agent": "NPG"}, {"env_step": 583680, "rew": -7.2815, "rew_std": 0.6265, "Agent": "NPG"}, {"env_step": 614400, "rew": -6.7526, "rew_std": 0.7363, "Agent": "NPG"}, {"env_step": 645120, "rew": -5.9064, "rew_std": 0.6141, "Agent": "NPG"}, {"env_step": 675840, "rew": -6.8038, "rew_std": 1.1164, "Agent": "NPG"}, {"env_step": 706560, "rew": -6.0693, "rew_std": 0.5347, "Agent": "NPG"}, {"env_step": 737280, "rew": -5.3244, "rew_std": 0.3901, "Agent": "NPG"}, {"env_step": 768000, "rew": -5.8036, "rew_std": 0.6029, "Agent": "NPG"}, {"env_step": 798720, "rew": -5.6529, "rew_std": 0.4782, "Agent": "NPG"}, {"env_step": 829440, "rew": -5.6872, "rew_std": 0.5073, "Agent": "NPG"}, {"env_step": 860160, "rew": -5.8134, "rew_std": 0.8252, "Agent": "NPG"}, {"env_step": 890880, "rew": -5.0251, "rew_std": 0.5694, "Agent": "NPG"}, {"env_step": 921600, "rew": -5.3842, "rew_std": 0.5721, "Agent": "NPG"}, {"env_step": 952320, "rew": -4.4665, "rew_std": 0.5124, "Agent": "NPG"}, {"env_step": 983040, "rew": -5.1101, "rew_std": 0.6535, "Agent": "NPG"}, {"env_step": 1013760, "rew": -5.1211, "rew_std": 0.5592, "Agent": "NPG"}, {"env_step": 1044480, "rew": -4.7359, "rew_std": 0.4729, "Agent": "NPG"}, {"env_step": 1075200, "rew": -5.153, "rew_std": 0.5877, "Agent": "NPG"}, {"env_step": 1105920, "rew": -4.7943, "rew_std": 0.4596, "Agent": "NPG"}, {"env_step": 1136640, "rew": -5.0972, "rew_std": 0.6443, "Agent": "NPG"}, {"env_step": 1167360, "rew": -4.8796, "rew_std": 0.32, "Agent": "NPG"}, {"env_step": 1198080, "rew": -4.6473, "rew_std": 0.3981, "Agent": "NPG"}, {"env_step": 1228800, "rew": -5.2037, "rew_std": 0.4172, "Agent": "NPG"}, {"env_step": 1259520, "rew": -5.2947, "rew_std": 0.6223, "Agent": "NPG"}, {"env_step": 1290240, "rew": -4.6651, "rew_std": 0.3997, "Agent": "NPG"}, {"env_step": 1320960, "rew": -5.3025, "rew_std": 0.5021, "Agent": "NPG"}, {"env_step": 1351680, "rew": -4.835, "rew_std": 0.8279, "Agent": "NPG"}, {"env_step": 1382400, "rew": -4.4981, "rew_std": 0.395, "Agent": "NPG"}, {"env_step": 1413120, "rew": -4.3411, "rew_std": 0.5186, "Agent": "NPG"}, {"env_step": 1443840, "rew": -3.8429, "rew_std": 0.4409, "Agent": "NPG"}, {"env_step": 1474560, "rew": -4.6336, "rew_std": 0.5871, "Agent": "NPG"}, {"env_step": 1505280, "rew": -4.4535, "rew_std": 0.4835, "Agent": "NPG"}, {"env_step": 1536000, "rew": -4.23, "rew_std": 0.3809, "Agent": "NPG"}, {"env_step": 1566720, "rew": -4.7947, "rew_std": 0.4871, "Agent": "NPG"}, {"env_step": 1597440, "rew": -4.8218, "rew_std": 0.3402, "Agent": "NPG"}, {"env_step": 1628160, "rew": -4.596, "rew_std": 0.3143, "Agent": "NPG"}, {"env_step": 1658880, "rew": -4.2059, "rew_std": 0.4831, "Agent": "NPG"}, {"env_step": 1689600, "rew": -4.467, "rew_std": 0.4294, "Agent": "NPG"}, {"env_step": 1720320, "rew": -3.9726, "rew_std": 0.5904, "Agent": "NPG"}, {"env_step": 1751040, "rew": -4.6491, "rew_std": 0.4616, "Agent": "NPG"}, {"env_step": 1781760, "rew": -4.0432, "rew_std": 0.3973, "Agent": "NPG"}, {"env_step": 1812480, "rew": -4.8602, "rew_std": 0.4932, "Agent": "NPG"}, {"env_step": 1843200, "rew": -4.4908, "rew_std": 0.2431, "Agent": "NPG"}, {"env_step": 1873920, "rew": -4.4493, "rew_std": 0.2925, "Agent": "NPG"}, {"env_step": 1904640, "rew": -4.1175, "rew_std": 0.3992, "Agent": "NPG"}, {"env_step": 1935360, "rew": -4.0126, "rew_std": 0.4803, "Agent": "NPG"}, {"env_step": 1966080, "rew": -4.6626, "rew_std": 0.2311, "Agent": "NPG"}, {"env_step": 1996800, "rew": -3.8578, "rew_std": 0.3729, "Agent": "NPG"}, {"env_step": 2027520, "rew": -4.4393, "rew_std": 0.5348, "Agent": "NPG"}, {"env_step": 2058240, "rew": -5.2012, "rew_std": 0.6865, "Agent": "NPG"}, {"env_step": 2088960, "rew": -4.7323, "rew_std": 0.4785, "Agent": "NPG"}, {"env_step": 2119680, "rew": -4.6148, "rew_std": 0.3647, "Agent": "NPG"}, {"env_step": 2150400, "rew": -4.9756, "rew_std": 0.4352, "Agent": "NPG"}, {"env_step": 2181120, "rew": -5.449, "rew_std": 0.5127, "Agent": "NPG"}, {"env_step": 2211840, "rew": -3.9708, "rew_std": 0.2708, "Agent": "NPG"}, {"env_step": 2242560, "rew": -5.0772, "rew_std": 0.6529, "Agent": "NPG"}, {"env_step": 2273280, "rew": -4.2406, "rew_std": 0.2822, "Agent": "NPG"}, {"env_step": 2304000, "rew": -5.1014, "rew_std": 0.2936, "Agent": "NPG"}, {"env_step": 2334720, "rew": -4.2671, "rew_std": 0.2057, "Agent": "NPG"}, {"env_step": 2365440, "rew": -3.8075, "rew_std": 0.3663, "Agent": "NPG"}, {"env_step": 2396160, "rew": -4.8169, "rew_std": 0.3568, "Agent": "NPG"}, {"env_step": 2426880, "rew": -3.9502, "rew_std": 0.4122, "Agent": "NPG"}, {"env_step": 2457600, "rew": -4.7268, "rew_std": 0.4072, "Agent": "NPG"}, {"env_step": 2488320, "rew": -5.4938, "rew_std": 0.3055, "Agent": "NPG"}, {"env_step": 2519040, "rew": -4.2352, "rew_std": 0.3984, "Agent": "NPG"}, {"env_step": 2549760, "rew": -4.3056, "rew_std": 0.7006, "Agent": "NPG"}, {"env_step": 2580480, "rew": -4.8314, "rew_std": 0.374, "Agent": "NPG"}, {"env_step": 2611200, "rew": -4.1952, "rew_std": 0.2762, "Agent": "NPG"}, {"env_step": 2641920, "rew": -3.6465, "rew_std": 0.3283, "Agent": "NPG"}, {"env_step": 2672640, "rew": -4.593, "rew_std": 0.4445, "Agent": "NPG"}, {"env_step": 2703360, "rew": -3.9484, "rew_std": 0.4034, "Agent": "NPG"}, {"env_step": 2734080, "rew": -4.0683, "rew_std": 0.4197, "Agent": "NPG"}, {"env_step": 2764800, "rew": -4.5761, "rew_std": 0.4453, "Agent": "NPG"}, {"env_step": 2795520, "rew": -4.2905, "rew_std": 0.4726, "Agent": "NPG"}, {"env_step": 2826240, "rew": -4.2228, "rew_std": 0.3405, "Agent": "NPG"}, {"env_step": 2856960, "rew": -5.2001, "rew_std": 0.6375, "Agent": "NPG"}, {"env_step": 2887680, "rew": -4.2828, "rew_std": 0.1875, "Agent": "NPG"}, {"env_step": 2918400, "rew": -4.2651, "rew_std": 0.2532, "Agent": "NPG"}, {"env_step": 2949120, "rew": -4.1655, "rew_std": 0.2444, "Agent": "NPG"}, {"env_step": 2979840, "rew": -4.496, "rew_std": 0.2794, "Agent": "NPG"}, {"env_step": 3010560, "rew": -4.151, "rew_std": 0.2886, "Agent": "NPG"}, {"env_step": 3041280, "rew": -5.0133, "rew_std": 0.3927, "Agent": "NPG"}, {"env_step": 3072000, "rew": -4.787, "rew_std": 0.3785, "Agent": "NPG"}] |