dqn python代码

以下是一个简单的DQN（Deep Q-Network）的Python实现，使用TensorFlow 2.0框架：

import gym
import tensorflow as tf
import numpy as np

class DQNAgent:
    def __init__(self, env):
        # 初始化环境和神经网络参数
        self.env = env
        self.input_shape = env.observation_space.shape
        self.output_shape = env.action_space.n
        self.learning_rate = 0.001
        self.gamma = 0.95
        self.epsilon = 1.0
        self.epsilon_decay = 0.995
        self.epsilon_min = 0.01
        self.memory = []
        self.batch_size = 32
        self.model = self.build_model()

    def build_model(self):
        # 构建神经网络模型
        model = tf.keras.models.Sequential()
        model.add(tf.keras.layers.Dense(24, input_shape=self.input_shape, activation='relu'))
        model.add(tf.keras.layers.Dense(24, activation='relu'))
        model.add(tf.keras.layers.Dense(self.output_shape, activation='linear'))
        model.compile(loss='mse', optimizer=tf.keras.optimizers.Adam(lr=self.learning_rate))
        return model

    def act(self, state):
        # 选择行动
        if np.random.rand() <= self.epsilon:
            return self.env.action_space.sample()
        else:
            return np.argmax(self.model.predict(state))

    def remember(self, state, action, reward, next_state, done):
        # 存储经验
        self.memory.append((state, action, reward, next_state, done))

    def replay(self):
        # 经验回放
        if len(self.memory) < self.batch_size:
            return
        batch = np.random.choice(self.memory, self.batch_size)
        for state, action, reward, next_state, done in batch:
            target = reward
            if not done:
                target = reward + self.gamma * np.amax(self.model.predict(next_state)[0])
            target_f = self.model.predict(state)
            target_f[0][action] = target
            self.model.fit(state, target_f, epochs=1, verbose=0)
        if self.epsilon > self.epsilon_min:
            self.epsilon *= self.epsilon_decay

    def train(self, episodes):
        # 开始训练
        for i in range(episodes):
            state = self.env.reset()
            state = np.reshape(state, [1, self.input_shape[0]])
            done = False
            score = 0
            while not done:
                action = self.act(state)
                next_state, reward, done, info = self.env.step(action)
                next_state = np.reshape(next_state, [1, self.input_shape[0]])
                self.remember(state, action, reward, next_state, done)
                state = next_state
                score += reward
            self.replay()
            print('Episode: %d, Score: %d, Epsilon: %.2f' % (i, score, self.epsilon))

if __name__ == "__main__":
    env = gym.make('CartPole-v0')
    agent = DQNAgent(env)
    agent.train(1000)

这个代码实现了一个DQN智能体，用于在OpenAI Gym的CartPole任务中学习。 该智能体使用经验回放来训练其神经网络，以使其能够预测最佳行动，并且逐渐减小其随机探索率，以便更多地依赖于其神经网络的输出。