def env_agent_config(cfg, seed=1):
env = NormalizedActions(gym.make(cfg.env_name)) # 装饰action噪声
env.seed(seed) # 随机种子
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.shape[0]
agent = DDPG(state_dim, action_dim, cfg)
return env, agent
while not done:
i_step += 1
action = agent.choose_action(state)
action = ou_noise.get_action(action, i_step) # 即paper中的random process
next_state, reward, done, _ = env.step(action)
ep_reward += reward
agent.memory.push(state, action, reward, next_state, done)
agent.update()
state = next_state
print('Episode:{}/{}, Reward:{}'.format(i_episode+1,cfg.train_eps,ep_reward))
ep_steps.append(i_step)
rewards.append(ep_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 = DDPGConfig()
env = NormalizedActions(gym.make("Pendulum-v0"))
env.seed(1) # 设置env随机种子
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.shape[0]
agent = DDPG(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)
state = next_state
if done:
break
print('Episode:{}/{}, Reward:{}, Steps:{}, Done:{}'.format(
i_episode + 1, cfg.train_eps, ep_reward, i_step + 1, done))
ep_steps.append(i_step)
rewards.append(ep_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 = DDPGConfig()
env = NormalizedActions(gym.make("Pendulum-v0"))
env.seed(1) # 设置env随机种子
n_states = env.observation_space.shape[0]
n_actions = env.action_space.shape[0]
agent = DDPG(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)