用python写用Q-learning算法控制倒立摆的代码

好的，这是一个技术问题，我可以回答。你可以参考下面的代码：

import gym
import numpy as np

env = gym.make('InvertedPendulum-v2')

# Initialize Q table
num_states = env.observation_space.shape[0]
num_actions = env.action_space.shape[0]
q_table = np.zeros((num_states, num_actions))

# Set hyperparameters
alpha = 0.1
gamma = 0.99
epsilon = 1.0
epsilon_decay = 0.999

# Run episodes
for i_episode in range(10000):
    state = env.reset()
    done = False
    while not done:
        # Choose action
        if np.random.random() > epsilon:
            action = np.argmax(q_table[state])
        else:
            action = env.action_space.sample()

        # Take action and observe new state and reward
        next_state, reward, done, _ = env.step(action)

        # Update Q-table
        td_target = reward + gamma * np.max(q_table[next_state])
        td_error = td_target - q_table[state][action]
        q_table[state][action] += alpha * td_error

        # Update state
        state = next_state

    # Decay epsilon
    epsilon *= epsilon_decay

    # Print episode number and total reward
    if i_episode % 100 == 0:
        total_reward = 0
        state = env.reset()
        done = False
        while not done:
            action = np.argmax(q_table[state])
            next_state, reward, done, _ = env.step(action)
            total_reward += reward
            state = next_state
        print(f'Episode {i_episode}: total reward = {total_reward}')