import gym, osfrom itertools import countimport paddleimport paddle.nn as nnimport paddle.optimizer as optimimport paddle.nn.functional as Ffrom paddle.distribution import Categorical登录后复制 ? ?

三、实施演员-评论家网络

这个网络学习两个功能：

• 演员Actor：它将环境的状态作为输入，并为其动作空间中的每个动作返回一个概率值。
• 评论家Critic：它将我们的环境状态作为输入，并返回对未来总回报的估计。

device = paddle.get_device()env = gym.make(”CartPole-v0“) ### 或者 env = gym.make(”CartPole-v0“).unwrapped 开启无锁定环境训练state_size = env.observation_space.shape[0]action_size = env.action_space.nlr = 0.001##定义“演员”网络class Actor(nn.Layer): def __init__(self, state_size, action_size): super(Actor, self).__init__() self.state_size = state_size self.action_size = action_size self.linear1 = nn.Linear(self.state_size, 128) self.linear2 = nn.Linear(128, 256) self.linear3 = nn.Linear(256, self.action_size) def forward(self, state): output = F.relu(self.linear1(state)) output = F.relu(self.linear2(output)) output = self.linear3(output) distribution = Categorical(F.softmax(output, axis=-1)) return distribution##定义“评论家”网络class Critic(nn.Layer): def __init__(self, state_size, action_size): super(Critic, self).__init__() self.state_size = state_size self.action_size = action_size self.linear1 = nn.Linear(self.state_size, 128) self.linear2 = nn.Linear(128, 256) self.linear3 = nn.Linear(256, 1) def forward(self, state): output = F.relu(self.linear1(state)) output = F.relu(self.linear2(output)) value = self.linear3(output) return value登录后复制 ? ?

四、训练模型

def compute_returns(next_value, rewards, masks, gamma=0.99): R = next_value returns = [] for step in reversed(range(len(rewards))): R = rewards[step] + gamma * R * masks[step] returns.insert(0, R) return returns## 定义训练过程def trainIters(actor, critic, n_iters): optimizerA = optim.Adam(lr, parameters=actor.parameters()) optimizerC = optim.Adam(lr, parameters=critic.parameters()) for iter in range(n_iters): state = env.reset() log_probs = [] values = [] rewards = [] masks = [] entropy = 0 env.reset() for i in count(): # env.render() state = paddle.to_tensor(state,dtype=”float32“,place=device) dist, value = actor(state), critic(state) action = dist.sample([1]) next_state, reward, done, _ = env.step(action.cpu().squeeze(0).numpy()) #env.step(action.cpu().squeeze(0).numpy()) log_prob = dist.log_prob(action); entropy += dist.entropy().mean() log_probs.append(log_prob) values.append(value) rewards.append(paddle.to_tensor([reward], dtype=”float32“, place=device)) masks.append(paddle.to_tensor([1-done], dtype=”float32“, place=device)) state = next_state if done: if iter % 10 == 0: print('Iteration: {}, Score: {}'.format(iter, i)) break next_state = paddle.to_tensor(next_state, dtype=”float32“, place=device) next_value = critic(next_state) returns = compute_returns(next_value, rewards, masks) log_probs = paddle.concat(log_probs) returns = paddle.concat(returns).detach() values = paddle.concat(values) advantage = returns - values actor_loss = -(log_probs * advantage.detach()).mean() critic_loss = advantage.pow(2).mean() optimizerA.clear_grad() optimizerC.clear_grad() actor_loss.backward() critic_loss.backward() optimizerA.step() optimizerC.step() paddle.save(actor.state_dict(), 'model/actor.pdparams') paddle.save(critic.state_dict(), 'model/critic.pdparams') env.close()if __name__ == '__main__': if os.path.exists('model/actor.pdparams'): actor = Actor(state_size, action_size) model_state_dict = paddle.load('model/actor.pdparams') actor.set_state_dict(model_state_dict ) print('Actor Model loaded') else: actor = Actor(state_size, action_size) if os.path.exists('model/critic.pdparams'): critic = Critic(state_size, action_size) model_state_dict = paddle.load('model/critic.pdparams') critic.set_state_dict(model_state_dict ) print('Critic Model loaded') else: critic = Critic(state_size, action_size) trainIters(actor, critic, n_iters=201)登录后复制 ? ? ? ?

Iteration: 0, Score: 19Iteration: 10, Score: 59Iteration: 20, Score: 24Iteration: 30, Score: 33Iteration: 40, Score: 39Iteration: 50, Score: 62Iteration: 60, Score: 44Iteration: 70, Score: 59Iteration: 80, Score: 21Iteration: 90, Score: 85Iteration: 100, Score: 152Iteration: 110, Score: 103Iteration: 120, Score: 69Iteration: 130, Score: 170Iteration: 140, Score: 199Iteration: 150, Score: 197Iteration: 160, Score: 199Iteration: 170, Score: 199Iteration: 180, Score: 163Iteration: 190, Score: 199Iteration: 200, Score: 199登录后复制 ? ? ? ?

开启无锁定环境训练

200分就是上限，还不能体现模型的能力，现在咱们开启无锁定环境的训练,将env = gym.make("CartPole-v0").unwrapped ,可以适当提高训练轮次。 （所有代码均已封装到train.py文件中，并用vdl记录）

!python train.py登录后复制 ? ? ? ?

W0303 17:18:01.972481 3940 device_context.cc:362] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1W0303 17:18:01.977756 3940 device_context.cc:372] device: 0, cuDNN Version: 7.6.Actor Model loadedCritic Model loadedIteration: 0, Score: 325登录后复制 ? ? ? ?

这是用vdl记录的Agent可以连续保持平衡的轮数的记录,最大值已经高达131540了，这是一个惊人的数字。