def env_agent_config(cfg, seed=1):
env = gym.make(cfg.env)
env.seed(seed)
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.n
agent = DQN(state_dim, action_dim, cfg)
return env, agent
if i_episode % cfg.target_update == 0:
agent.target_net.load_state_dict(agent.policy_net.state_dict())
print('Episode:{}/{}, Reward:{}, Steps:{}, Done:{}'.format(
i_episode + 1, cfg.train_eps, ep_reward, i_step, done))
ep_steps.append(i_step)
rewards.append(ep_reward)
# 计算滑动窗口的reward
if ma_rewards:
ma_rewards.append(0.9 * ma_rewards[-1] + 0.1 * ep_reward)
else:
ma_rewards.append(ep_reward)
print('Complete training！')
return rewards, ma_rewards
if __name__ == "__main__":
cfg = DQNConfig()
env = gym.make('CartPole-v0').unwrapped # 可google为什么unwrapped gym，此处一般不需要
env.seed(1) # 设置env随机种子
n_states = env.observation_space.shape[0]
n_actions = env.action_space.n
agent = DQN(n_states, n_actions, cfg)
rewards, ma_rewards = train(cfg, env, agent)
agent.save(path=SAVED_MODEL_PATH)
save_results(rewards, ma_rewards, tag='train', path=RESULT_PATH)
plot_rewards(rewards,
ma_rewards,
tag="train",
algo=cfg.algo,
path=RESULT_PATH)
agent.update()
if i_episode % cfg.target_update == 0:
agent.target_net.load_state_dict(agent.policy_net.state_dict())
print('Episode:{}/{}, Reward:{}'.format(i_episode + 1, cfg.train_eps,
ep_reward))
rewards.append(ep_reward)
# 计算滑动窗口的reward
if ma_rewards:
ma_rewards.append(0.9 * ma_rewards[-1] + 0.1 * ep_reward)
else:
ma_rewards.append(ep_reward)
print('Complete training！')
return rewards, ma_rewards
if __name__ == "__main__":
cfg = DQNConfig()
env = gym.make('CartPole-v0')
env.seed(1)
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.n
agent = DQN(state_dim, action_dim, cfg)
rewards, ma_rewards = train(cfg, env, agent)
agent.save(path=SAVED_MODEL_PATH)
save_results(rewards, ma_rewards, tag='train', path=RESULT_PATH)
plot_rewards(rewards,
ma_rewards,
tag="train",
algo=cfg.algo,
path=RESULT_PATH)
# 更新目标网络
if i_episode % cfg.target_update == 0:
agent.target_net.load_state_dict(agent.policy_net.state_dict())
print('Episode:{}/{},Reward:{}'.format(i_episode + 1, cfg.train_eps,
ep_reward))
rewards.append(ep_reward)
# 计算滑动窗口的reward
if ma_rewards:
ma_rewards.append(0.9 * ma_rewards[-1] + 0.1 * ep_reward)
else:
ma_rewards.append(ep_reward)
print('Complete training')
return rewards, ma_rewards
if __name__ == "__main__":
cfg = DQNConfig()
env = gym.make(cfg.env)
env.seed(1)
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.n
agent = DQN(state_dim, action_dim, cfg)
rewards, ma_rewards = train(cfg, env, agent)
make_dir(cfg.result_path)
agent.save(path=cfg.result_path)
save_results(rewards, ma_rewards, tag='train', path=cfg.result_path)
plot_rewards(rewards,
ma_rewards,
tag="train",
algo=cfg.algo,
path=cfg.result_path)
ep_reward += reward
agent.memory.push(state, action, reward, next_state, done)
state = next_state
agent.update()
if i_episode % cfg.target_update == 0:
agent.target_net.load_state_dict(agent.policy_net.state_dict())
print('Episode:{}/{}, Reward:{}'.format(i_episode+1, cfg.train_eps, ep_reward))
rewards.append(ep_reward)
# 计算滑动窗口的reward
if ma_rewards:
ma_rewards.append(0.9*ma_rewards[-1]+0.1*ep_reward)
else:
ma_rewards.append(ep_reward)
print('Complete training！')
return rewards, ma_rewards
if __name__ == "__main__":
cfg = DQNConfig()
env = gym.make(cfg.env)
env.seed(1)
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.n
agent = DQN(state_dim, action_dim, cfg)
rewards, ma_rewards = train(cfg, env, agent)
make_dir(cfg.result_path, cfg.model_path)
agent.save(path=cfg.model_path)
save_results(rewards, ma_rewards, tag='train', path=cfg.result_path)
plot_rewards(rewards, ma_rewards, tag="train",
algo=cfg.algo, path=cfg.result_path)