Question

仅供参考：我正在尝试将强化学习机制应用于分类任务。我知道做深度学习可以在任务中胜过rl是没有用的。无论如何，我正在做研究。

如果特工正确为正1或不为负-1，我会给予奖励并使用predicted_action（predicted_class）和奖励计算损失FUNC

这是我的错误，我仍然无济于事...看了S.O中的一些答案，但仍然遇到麻烦

错误是;张量的元素0不需要grad并且没有grad_fn

如果我的英语能力使您感到不舒服，对不起非常感谢

 # creating model
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        self.pipe = nn.Sequential(nn.Linear(9, 120),
                                 nn.ReLU(),
                                 nn.Linear(120, 64),
                                 nn.ReLU(),
                                 nn.Linear(64,2),
                                 nn.Softmax()
                                 )

    def forward(self, x):
        return self.pipe(x)


def env_step(action, label, size):
    total_reward = []

    for i in range(size):
        reward = 0

        if action[i] == label[i]:
            total_reward.append(reward+1)
            continue
        else:
            total_reward.append(reward-1)
            continue

    return total_reward




if __name__=='__main__':
    epoch_size = 100
    net = Net()
    criterion = nn.MSELoss()
    optimizer = optim.Adam(params=net.parameters(), lr=0.01)

    total_loss = deque(maxlen = 50)

    for epoch in range(epoch_size):
        batch_index = 0
        for i in range(13):
            # batch sample
            batch_xs = torch.FloatTensor(train_state[batch_index: batch_index+50])   # make tensor
            batch_ys = torch.from_numpy(train_label[batch_index: batch_index+50]).type('torch.LongTensor')  # make tensor

            # action_prob; e.g classification prob
            actions_prob = net(batch_xs)                                
            #print(actions_prob)
            action = torch.argmax(actions_prob, dim=1).unsqueeze(1)    
            #print(action)
            reward = np.array(env_step(action, batch_ys, 50))  
            #print(reward)

            reward = torch.from_numpy(reward).unsqueeze(1).type('torch.FloatTensor')
            #print(reward)
            action = action.type('torch.FloatTensor')

            optimizer.zero_grad()
            loss = criterion(action, reward)    
            loss.backward()
            optimizer.step()


            batch_index += 50

Answer 1

action是由argmax函数产生的，不可区分。相反，您要承担在奖励和采取行动的负责任概率之间的损失。

通常，在学习策略中为策略选择的“损失”就是所谓的score function： link

对于采取的行动a，责任概率的对数乘以所获得的奖励。

张量的元素0不需要grad并且没有grad_fn

1 个答案: