使用Python实现深度学习模型：强化学习与深度Q网络（DQN）

pip install gym numpy tensorflow

import gym

# 创建CartPole环境
env = gym.make('CartPole-v1')
state = env.reset()
print('State:', state)

import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from collections import deque
import random

def build_model(state_size, action_size):
    model = Sequential()
    model.add(Dense(24, input_dim=state_size, activation='relu'))
    model.add(Dense(24, activation='relu'))
    model.add(Dense(action_size, activation='linear'))
    model.compile(loss='mse', optimizer=tf.keras.optimizers.Adam(learning_rate=0.001))
    return model

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    # 折扣因子
        self.epsilon = 1.0   # 探索率
        self.epsilon_min = 0.01
        self.epsilon_decay = 0.995
        self.model = build_model(state_size, action_size)

    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 random.randrange(self.action_size)
        q_values = self.model.predict(state)
        return np.argmax(q_values[0])

    def replay(self, batch_size):
        minibatch = random.sample(self.memory, batch_size)
        for state, action, reward, next_state, done in minibatch:
            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

import numpy as np

# 初始化环境和DQN智能体
env = gym.make('CartPole-v1')
state_size = env.observation_space.shape[0]
action_size = env.action_space.n
agent = DQNAgent(state_size, action_size)
episodes = 1000
batch_size = 32

for e in range(episodes):
    state = env.reset()
    state = np.reshape(state, [1, state_size])
    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
        if done:
            print(f"Episode: {e}/{episodes}, Score: {time}, Epsilon: {agent.epsilon:.2}")
            break
        if len(agent.memory) > batch_size:
            agent.replay(batch_size)

for e in range(10):
    state = env.reset()
    state = np.reshape(state, [1, state_size])
    for time in range(500):
        env.render()
        action = agent.act(state)
        next_state, reward, done, _ = env.step(action)
        next_state = np.reshape(next_state, [1, state_size])
        state = next_state
        if done:
            print(f"Test Episode: {e}/{10}, Score: {time}")
            break
env.close()