thu-ml · Mehooz · Mar 25, 2020 · Mar 26, 2020 · Mar 26, 2020 · Mar 26, 2020
diff --git a/docs/_static/images/Ant-v2.png b/docs/_static/images/Ant-v2.png
diff --git a/examples/ant_v2_ddpg.py b/examples/ant_v2_ddpg.py
@@ -0,0 +1,105 @@
+import gym
+import torch
+import pprint
+import argparse
+import numpy as np
+from torch.utils.tensorboard import SummaryWriter
+
+from tianshou.policy import DDPGPolicy
+from tianshou.trainer import offpolicy_trainer
+from tianshou.data import Collector, ReplayBuffer
+from tianshou.env import VectorEnv, SubprocVectorEnv
+
+if __name__ == '__main__':
+    from continuous_net import Actor, Critic
+else:  # pytest
+    from test.continuous.net import Actor, Critic
+
+
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--task', type=str, default='Ant-v2')
+    parser.add_argument('--seed', type=int, default=1626)
+    parser.add_argument('--buffer-size', type=int, default=20000)
+    parser.add_argument('--actor-lr', type=float, default=1e-4)
+    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('--exploration-noise', type=float, default=0.1)
+    parser.add_argument('--epoch', type=int, default=100)
+    parser.add_argument('--step-per-epoch', type=int, default=2400)
+    parser.add_argument('--collect-per-step', type=int, default=4)
+    parser.add_argument('--batch-size', type=int, default=128)
+    parser.add_argument('--layer-num', type=int, default=1)
+    parser.add_argument('--training-num', type=int, default=8)
+    parser.add_argument('--test-num', type=int, default=100)
+    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')
+    args = parser.parse_known_args()[0]
+    return args
+
+
+def test_ddpg(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]
+    # train_envs = gym.make(args.task)
+    train_envs = VectorEnv(
+        [lambda: gym.make(args.task) for _ in range(args.training_num)])
+    # 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
+    actor = Actor(
+        args.layer_num, args.state_shape, args.action_shape,
+        args.max_action, args.device
+    ).to(args.device)
+    actor_optim = torch.optim.Adam(actor.parameters(), lr=args.actor_lr)
+    critic = Critic(
+        args.layer_num, args.state_shape, args.action_shape, args.device
+    ).to(args.device)
+    critic_optim = torch.optim.Adam(critic.parameters(), lr=args.critic_lr)
+    policy = DDPGPolicy(
+        actor, actor_optim, critic, critic_optim,
+        args.tau, args.gamma, args.exploration_noise,
+        [env.action_space.low[0], env.action_space.high[0]],
+        reward_normalization=True, ignore_done=True)
+    # collector
+    train_collector = Collector(
+        policy, train_envs, ReplayBuffer(args.buffer_size))
+    test_collector = Collector(policy, test_envs)
+    # log
+    writer = SummaryWriter(args.logdir + '/' + 'ddpg')
+
+    def stop_fn(x):
+        return x >= env.spec.reward_threshold
+
+    # trainer
+    result = offpolicy_trainer(
+        policy, train_collector, test_collector, args.epoch,
+        args.step_per_epoch, args.collect_per_step, args.test_num,
+        args.batch_size, stop_fn=stop_fn, writer=writer, task=args.task)
+    assert stop_fn(result['best_reward'])
+    train_collector.close()
+    test_collector.close()
+    if __name__ == '__main__':
+        pprint.pprint(result)
+        # Let's watch its performance!
+        env = gym.make(args.task)
+        collector = Collector(policy, env)
+        result = collector.collect(n_episode=1, render=args.render)
+        print(f'Final reward: {result["rew"]}, length: {result["len"]}')
+        collector.close()
+
+
+if __name__ == '__main__':
+    test_ddpg()
diff --git a/examples/ant_v2_sac.py b/examples/ant_v2_sac.py
@@ -0,0 +1,110 @@
+import gym
+import torch
+import pprint
+import argparse
+import numpy as np
+from torch.utils.tensorboard import SummaryWriter
+
+from tianshou.policy import SACPolicy
+from tianshou.trainer import offpolicy_trainer
+from tianshou.data import Collector, ReplayBuffer
+from tianshou.env import VectorEnv, SubprocVectorEnv
+
+if __name__ == '__main__':
+    from continuous_net import ActorProb, Critic
+else:  # pytest
+    from test.continuous.net import ActorProb, Critic
+
+
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--task', type=str, default='Ant-v2')
+    parser.add_argument('--seed', type=int, default=1626)
+    parser.add_argument('--buffer-size', type=int, default=20000)
+    parser.add_argument('--actor-lr', type=float, default=3e-4)
+    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('--epoch', type=int, default=100)
+    parser.add_argument('--step-per-epoch', type=int, default=2400)
+    parser.add_argument('--collect-per-step', type=int, default=10)
+    parser.add_argument('--batch-size', type=int, default=128)
+    parser.add_argument('--layer-num', type=int, default=1)
+    parser.add_argument('--training-num', type=int, default=8)
+    parser.add_argument('--test-num', type=int, default=100)
+    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')
+    args = parser.parse_known_args()[0]
+    return 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]
+    # train_envs = gym.make(args.task)
+    train_envs = VectorEnv(
+        [lambda: gym.make(args.task) for _ in range(args.training_num)])
+    # 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
+    actor = ActorProb(
+        args.layer_num, args.state_shape, args.action_shape,
+        args.max_action, args.device
+    ).to(args.device)
+    actor_optim = torch.optim.Adam(actor.parameters(), lr=args.actor_lr)
+    critic1 = Critic(
+        args.layer_num, args.state_shape, args.action_shape, args.device
+    ).to(args.device)
+    critic1_optim = torch.optim.Adam(critic1.parameters(), lr=args.critic_lr)
+    critic2 = Critic(
+        args.layer_num, args.state_shape, args.action_shape, args.device
+    ).to(args.device)
+    critic2_optim = torch.optim.Adam(critic2.parameters(), lr=args.critic_lr)
+    policy = SACPolicy(
+        actor, actor_optim, critic1, critic1_optim, critic2, critic2_optim,
+        args.tau, args.gamma, args.alpha,
+        [env.action_space.low[0], env.action_space.high[0]],
+        reward_normalization=True, ignore_done=True)
+    # collector
+    train_collector = Collector(
+        policy, train_envs, ReplayBuffer(args.buffer_size))
+    test_collector = Collector(policy, test_envs)
+    # train_collector.collect(n_step=args.buffer_size)
+    # log
+    writer = SummaryWriter(args.logdir + '/' + 'sac')
+
+    def stop_fn(x):
+        return x >= env.spec.reward_threshold
+
+    # trainer
+    result = offpolicy_trainer(
+        policy, train_collector, test_collector, args.epoch,
+        args.step_per_epoch, args.collect_per_step, args.test_num,
+        args.batch_size, stop_fn=stop_fn, writer=writer, task=args.task)
+    assert stop_fn(result['best_reward'])
+    train_collector.close()
+    test_collector.close()
+    if __name__ == '__main__':
+        pprint.pprint(result)
+        # Let's watch its performance!
+        env = gym.make(args.task)
+        collector = Collector(policy, env)
+        result = collector.collect(n_episode=1, render=args.render)
+        print(f'Final reward: {result["rew"]}, length: {result["len"]}')
+        collector.close()
+
+
+if __name__ == '__main__':
+    test_sac()
diff --git a/examples/ant_v2_td3.py b/examples/ant_v2_td3.py
@@ -0,0 +1,114 @@
+import gym
+import torch
+import pprint
+import argparse
+import numpy as np
+from torch.utils.tensorboard import SummaryWriter
+
+from tianshou.policy import TD3Policy
+from tianshou.trainer import offpolicy_trainer
+from tianshou.data import Collector, ReplayBuffer
+from tianshou.env import VectorEnv, SubprocVectorEnv
+
+if __name__ == '__main__':
+    from continuous_net import Actor, Critic
+else:  # pytest
+    from test.continuous.net import Actor, Critic
+
+
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--task', type=str, default='Ant-v2')
+    parser.add_argument('--seed', type=int, default=1626)
+    parser.add_argument('--buffer-size', type=int, default=20000)
+    parser.add_argument('--actor-lr', type=float, default=3e-4)
+    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('--exploration-noise', type=float, default=0.1)
+    parser.add_argument('--policy-noise', type=float, default=0.2)
+    parser.add_argument('--noise-clip', type=float, default=0.5)
+    parser.add_argument('--update-actor-freq', type=int, default=2)
+    parser.add_argument('--epoch', type=int, default=100)
+    parser.add_argument('--step-per-epoch', type=int, default=2400)
+    parser.add_argument('--collect-per-step', type=int, default=10)
+    parser.add_argument('--batch-size', type=int, default=128)
+    parser.add_argument('--layer-num', type=int, default=1)
+    parser.add_argument('--training-num', type=int, default=8)
+    parser.add_argument('--test-num', type=int, default=100)
+    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')
+    args = parser.parse_known_args()[0]
+    return args
+
+
+def test_td3(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]
+    # train_envs = gym.make(args.task)
+    train_envs = VectorEnv(
+        [lambda: gym.make(args.task) for _ in range(args.training_num)])
+    # 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
+    actor = Actor(
+        args.layer_num, args.state_shape, args.action_shape,
+        args.max_action, args.device
+    ).to(args.device)
+    actor_optim = torch.optim.Adam(actor.parameters(), lr=args.actor_lr)
+    critic1 = Critic(
+        args.layer_num, args.state_shape, args.action_shape, args.device
+    ).to(args.device)
+    critic1_optim = torch.optim.Adam(critic1.parameters(), lr=args.critic_lr)
+    critic2 = Critic(
+        args.layer_num, args.state_shape, args.action_shape, args.device
+    ).to(args.device)
+    critic2_optim = torch.optim.Adam(critic2.parameters(), lr=args.critic_lr)
+    policy = TD3Policy(
+        actor, actor_optim, critic1, critic1_optim, critic2, critic2_optim,
+        args.tau, args.gamma, args.exploration_noise, args.policy_noise,
+        args.update_actor_freq, args.noise_clip,
+        [env.action_space.low[0], env.action_space.high[0]],
+        reward_normalization=True, ignore_done=True)
+    # collector
+    train_collector = Collector(
+        policy, train_envs, ReplayBuffer(args.buffer_size))
+    test_collector = Collector(policy, test_envs)
+    # train_collector.collect(n_step=args.buffer_size)
+    # log
+    writer = SummaryWriter(args.logdir + '/' + 'td3')
+
+    def stop_fn(x):
+        return x >= env.spec.reward_threshold
+
+    # trainer
+    result = offpolicy_trainer(
+        policy, train_collector, test_collector, args.epoch,
+        args.step_per_epoch, args.collect_per_step, args.test_num,
+        args.batch_size, stop_fn=stop_fn, writer=writer, task=args.task)
+    assert stop_fn(result['best_reward'])
+    train_collector.close()
+    test_collector.close()
+    if __name__ == '__main__':
+        pprint.pprint(result)
+        # Let's watch its performance!
+        env = gym.make(args.task)
+        collector = Collector(policy, env)
+        result = collector.collect(n_episode=1, render=args.render)
+        print(f'Final reward: {result["rew"]}, length: {result["len"]}')
+        collector.close()
+
+
+if __name__ == '__main__':
+    test_td3()