actor_critic.py 文件源码

def finish_episode():
    R = 0
    saved_actions = model.saved_actions
    policy_losses = []
    value_losses = []
    rewards = []
    for r in model.rewards[::-1]:
        R = r + args.gamma * R
        rewards.insert(0, R)
    rewards = torch.Tensor(rewards)
    rewards = (rewards - rewards.mean()) / (rewards.std() + np.finfo(np.float32).eps)
    for (log_prob, value), r in zip(saved_actions, rewards):
        reward = r - value.data[0, 0]
        policy_losses.append(-log_prob * reward)
        value_losses.append(F.smooth_l1_loss(value, Variable(torch.Tensor([r]))))
    optimizer.zero_grad()
    loss = torch.cat(policy_losses).sum() + torch.cat(value_losses).sum()
    loss.backward()
    optimizer.step()
    del model.rewards[:]
    del model.saved_actions[:]