DQN算法打印历代奖励值代码

好的，以下是使用DQN算法打印历代奖励值的代码示例：

import gym
import numpy as np
import tensorflow as tf
from collections import deque

class DQNAgent:
    def __init__(self, state_size, action_size):
        self.state_size = state_size
        self.action_size = action_size
        self.memory = deque(maxlen=2000)
        self.gamma = 0.95
        self.epsilon = 1.0
        self.epsilon_min = 0.01
        self.epsilon_decay = 0.995
        self.learning_rate = 0.001
        self.model = self._build_model()

    def _build_model(self):
        model = tf.keras.models.Sequential()
        model.add(tf.keras.layers.Dense(24, input_dim=self.state_size, activation='relu'))
        model.add(tf.keras.layers.Dense(24, activation='relu'))
        model.add(tf.keras.layers.Dense(self.action_size, activation='linear'))
        model.compile(loss='mse', optimizer=tf.keras.optimizers.Adam(lr=self.learning_rate))
        return model

    def remember(self, state, action, reward, next_state, done):
        self.memory.append((state, action, reward, next_state, done))

    def act(self, state):
        if np.random.rand() <= self.epsilon:
            return np.random.choice(self.action_size)
        act_values = self.model.predict(state)
        return np.argmax(act_values[0])

    def replay(self, batch_size):
        minibatch = np.array(random.sample(self.memory, batch_size))
        states = np.concatenate(minibatch[:,0], axis=0)
        actions = np.concatenate(minibatch[:,1], axis=0)
        rewards = minibatch[:,2]
        next_states = np.concatenate(minibatch[:,3], axis=0)
        dones = minibatch[:,4]
        targets = self.model.predict(states)
        next_state_targets = self.model.predict(next_states)
        for i in range(batch_size):
            if dones[i]:
                targets[i][actions[i]] = rewards[i]
            else:
                targets[i][actions[i]] = rewards[i] + self.gamma * np.amax(next_state_targets[i])
        self.model.fit(states, targets, epochs=1, verbose=0)
        if self.epsilon > self.epsilon_min:
            self.epsilon *= self.epsilon_decay

    def load(self, name):
        self.model.load_weights(name)

    def save(self, name):
        self.model.save_weights(name)

if __name__ == "__main__":
    env = gym.make('CartPole-v1')
    state_size = env.observation_space.shape[0]
    action_size = env.action_space.n
    agent = DQNAgent(state_size, action_size)
    done = False
    batch_size = 32
    num_episodes = 1000
    rewards = []
    for e in range(num_episodes):
        state = env.reset()
        state = np.reshape(state, [1, state_size])
        total_reward = 0
        for time in range(500):
            action = agent.act(state)
            next_state, reward, done, _ = env.step(action)
            reward = reward if not done else -10
            next_state = np.reshape(next_state, [1, state_size])
            agent.remember(state, action, reward, next_state, done)
            state = next_state
            total_reward += reward
            if done:
                print("episode: {}/{}, score: {}".format(e+1, num_episodes, time))
                rewards.append(total_reward)
                break
            if len(agent.memory) > batch_size:
                agent.replay(batch_size)
        if (e+1) % 10 == 0:
            agent.save("cartpole-dqn.h5")
    env.close()
    print("Average reward for last 100 episodes: ", np.mean(rewards[-100:]))

在上面的代码中，我们定义了一个`DQNAgent`类来实现DQN算法。`remember`方法用于存储经验回放，`act`方法用于选择动作，`replay`方法用于训练模型。在主程序中，我们使用`for`循环来运行多个episode，并在每个episode结束时打印分数。最后，我们通过计算最后100个episode的平均奖励来评估算法的性能。