def train(cfg,env,agent):
print('Start to train ! ')
ou_noise = OUNoise(env.action_space) # action noise
rewards = []
ma_rewards = [] # moving average rewards
ep_steps = []
for i_episode in range(cfg.train_eps):
state = env.reset()
ou_noise.reset()
done = False
ep_reward = 0
i_step = 0
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
def train(cfg, env, agent):
print('开始训练！')
print(f'环境：{cfg.env_name}，算法：{cfg.algo}，设备：{cfg.device}')
ou_noise = OUNoise(env.action_space) # 动作噪声
rewards = [] # 记录所有回合的奖励
ma_rewards = [] # 记录所有回合的滑动平均奖励
for i_ep in range(cfg.train_eps):
state = env.reset()
ou_noise.reset()
done = False
ep_reward = 0
i_step = 0
while not done:
i_step += 1
action = agent.choose_action(state)
action = ou_noise.get_action(action, i_step)
next_state, reward, done, _ = env.step(action)
ep_reward += reward
agent.memory.push(state, action, reward, next_state, done)
agent.update()
state = next_state
if (i_ep+1)%10 == 0:
print('回合：{}/{}，奖励：{:.2f}'.format(i_ep+1, cfg.train_eps, ep_reward))
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('完成训练！')
return rewards, ma_rewards