fix docs (#373)

- fix css style error
- fix mujoco benchmark result

docs/conf.py

@@ -90,8 +90,6 @@ html_logo = "_static/images/tianshou-logo.png"
 
 
 def setup(app):
-    app.add_js_file(
-        "https://cdnjs.cloudflare.com/ajax/libs/jquery/3.6.0/jquery.min.js")
     app.add_js_file("https://cdn.jsdelivr.net/npm/vega@5.20.2")
     app.add_js_file("https://cdn.jsdelivr.net/npm/vega-lite@5.1.0")
     app.add_js_file("https://cdn.jsdelivr.net/npm/vega-embed@6.17.0")

docs/index.rst

@@ -33,7 +33,7 @@ Welcome to Tianshou!
 
 Here is Tianshou's other features:
 
-* Elegant framework, using only ~2000 lines of code
+* Elegant framework, using only ~3000 lines of code
 * State-of-the-art `MuJoCo benchmark <https://github.com/thu-ml/tianshou/tree/master/examples/mujoco>`_
 * Support parallel environment simulation (synchronous or asynchronous) for all algorithms: :ref:`parallel_sampling`
 * Support recurrent state representation in actor network and critic network (RNN-style training for POMDP): :ref:`rnn_training`

docs/requirements.txt

@@ -3,4 +3,5 @@ tqdm
 torch
 numba
 tensorboard
+sphinx<4
 sphinxcontrib-bibtex

docs/tutorials/benchmark.rst

@@ -1,6 +1,7 @@
 Benchmark
 =========
 
+
 Mujoco Benchmark
 ----------------
 

examples/atari/atari_c51.py

@@ -62,7 +62,7 @@ def make_atari_env_watch(args):
 def test_c51(args=get_args()):
     env = make_atari_env(args)
     args.state_shape = env.observation_space.shape or env.observation_space.n
-    args.action_shape = env.env.action_space.shape or env.env.action_space.n
+    args.action_shape = env.action_space.shape or env.action_space.n
     # should be N_FRAMES x H x W
     print("Observations shape:", args.state_shape)
     print("Actions shape:", args.action_shape)

examples/atari/atari_dqn.py

@@ -59,7 +59,7 @@ def make_atari_env_watch(args):
 def test_dqn(args=get_args()):
     env = make_atari_env(args)
     args.state_shape = env.observation_space.shape or env.observation_space.n
-    args.action_shape = env.env.action_space.shape or env.env.action_space.n
+    args.action_shape = env.action_space.shape or env.action_space.n
     # should be N_FRAMES x H x W
     print("Observations shape:", args.state_shape)
     print("Actions shape:", args.action_shape)

examples/atari/atari_qrdqn.py

@@ -60,7 +60,7 @@ def make_atari_env_watch(args):
 def test_qrdqn(args=get_args()):
     env = make_atari_env(args)
     args.state_shape = env.observation_space.shape or env.observation_space.n
-    args.action_shape = env.env.action_space.shape or env.env.action_space.n
+    args.action_shape = env.action_space.shape or env.action_space.n
     # should be N_FRAMES x H x W
     print("Observations shape:", args.state_shape)
     print("Actions shape:", args.action_shape)