#!/usr/bin/env python3 import os import gym import torch import datetime import argparse import numpy as np from torch.utils.tensorboard import SummaryWriter from tianshou.policy import SACPolicy from tianshou.utils import BasicLogger from tianshou.env import SubprocVectorEnv from tianshou.utils.net.common import Net from tianshou.trainer import offpolicy_trainer from tianshou.utils.net.continuous import ActorProb, Critic from tianshou.data import Collector, ReplayBuffer, VectorReplayBuffer def get_args(): parser = argparse.ArgumentParser() parser.add_argument('--task', type=str, default='Ant-v3') parser.add_argument('--seed', type=int, default=0) parser.add_argument('--buffer-size', type=int, default=1000000) parser.add_argument('--hidden-sizes', type=int, nargs='*', default=[256, 256]) parser.add_argument('--actor-lr', type=float, default=1e-3) parser.add_argument('--critic-lr', type=float, default=1e-3) parser.add_argument('--gamma', type=float, default=0.99) parser.add_argument('--tau', type=float, default=0.005) parser.add_argument('--alpha', type=float, default=0.2) parser.add_argument('--auto-alpha', default=False, action='store_true') parser.add_argument('--alpha-lr', type=float, default=3e-4) parser.add_argument("--start-timesteps", type=int, default=10000) parser.add_argument('--epoch', type=int, default=200) parser.add_argument('--step-per-epoch', type=int, default=5000) parser.add_argument('--step-per-collect', type=int, default=1) parser.add_argument('--update-per-step', type=int, default=1) parser.add_argument('--n-step', type=int, default=1) parser.add_argument('--batch-size', type=int, default=256) parser.add_argument('--training-num', type=int, default=1) parser.add_argument('--test-num', type=int, default=10) parser.add_argument('--logdir', type=str, default='log') parser.add_argument('--render', type=float, default=0.) parser.add_argument( '--device', type=str, default='cuda' if torch.cuda.is_available() else 'cpu') parser.add_argument('--resume-path', type=str, default=None) return parser.parse_args() def test_sac(args=get_args()): env = gym.make(args.task) args.state_shape = env.observation_space.shape or env.observation_space.n args.action_shape = env.action_space.shape or env.action_space.n args.max_action = env.action_space.high[0] print("Observations shape:", args.state_shape) print("Actions shape:", args.action_shape) print("Action range:", np.min(env.action_space.low), np.max(env.action_space.high)) # train_envs = gym.make(args.task) if args.training_num > 1: train_envs = SubprocVectorEnv( [lambda: gym.make(args.task) for _ in range(args.training_num)]) else: train_envs = gym.make(args.task) # test_envs = gym.make(args.task) test_envs = SubprocVectorEnv( [lambda: gym.make(args.task) for _ in range(args.test_num)]) # seed np.random.seed(args.seed) torch.manual_seed(args.seed) train_envs.seed(args.seed) test_envs.seed(args.seed) # model net_a = Net(args.state_shape, hidden_sizes=args.hidden_sizes, device=args.device) actor = ActorProb( net_a, args.action_shape, max_action=args.max_action, device=args.device, unbounded=True, conditioned_sigma=True ).to(args.device) actor_optim = torch.optim.Adam(actor.parameters(), lr=args.actor_lr) net_c1 = Net(args.state_shape, args.action_shape, hidden_sizes=args.hidden_sizes, concat=True, device=args.device) net_c2 = Net(args.state_shape, args.action_shape, hidden_sizes=args.hidden_sizes, concat=True, device=args.device) critic1 = Critic(net_c1, device=args.device).to(args.device) critic1_optim = torch.optim.Adam(critic1.parameters(), lr=args.critic_lr) critic2 = Critic(net_c2, device=args.device).to(args.device) critic2_optim = torch.optim.Adam(critic2.parameters(), lr=args.critic_lr) if args.auto_alpha: target_entropy = -np.prod(env.action_space.shape) log_alpha = torch.zeros(1, requires_grad=True, device=args.device) alpha_optim = torch.optim.Adam([log_alpha], lr=args.alpha_lr) args.alpha = (target_entropy, log_alpha, alpha_optim) policy = SACPolicy( actor, actor_optim, critic1, critic1_optim, critic2, critic2_optim, action_range=[env.action_space.low[0], env.action_space.high[0]], tau=args.tau, gamma=args.gamma, alpha=args.alpha, estimation_step=args.n_step) # load a previous policy if args.resume_path: policy.load_state_dict(torch.load( args.resume_path, map_location=args.device )) print("Loaded agent from: ", args.resume_path) # collector if args.training_num > 1: buffer = VectorReplayBuffer(args.buffer_size, len(train_envs)) else: buffer = ReplayBuffer(args.buffer_size) train_collector = Collector(policy, train_envs, buffer, exploration_noise=True) test_collector = Collector(policy, test_envs) train_collector.collect(n_step=args.start_timesteps, random=True) # log log_path = os.path.join(args.logdir, args.task, 'sac', 'seed_' + str( args.seed) + '_' + datetime.datetime.now().strftime('%m%d-%H%M%S')) writer = SummaryWriter(log_path) writer.add_text("args", str(args)) logger = BasicLogger(writer) def save_fn(policy): torch.save(policy.state_dict(), os.path.join(log_path, 'policy.pth')) # trainer result = offpolicy_trainer( policy, train_collector, test_collector, args.epoch, args.step_per_epoch, args.step_per_collect, args.test_num, args.batch_size, save_fn=save_fn, logger=logger, update_per_step=args.update_per_step, test_in_train=False) # Let's watch its performance! policy.eval() test_envs.seed(args.seed) test_collector.reset() result = test_collector.collect(n_episode=args.test_num, render=args.render) print(f'Final reward: {result["rews"].mean()}, length: {result["lens"].mean()}') if __name__ == '__main__': test_sac()