基于stable-baseline3 强化学习DQN的lunar lander的稳定控制

依赖包

鉴于不同版本的gym与stable-baselines3会产生冲突，在成功的基础上记录：
gym == 0.21.0
stable-baselines3 == 1.6.2
安装代码：

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple gym==0.21.0
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple stable-baselines3[extra]==1.6.2

lunar lander随机初始化action

import gym


# Create environment
env = gym.make("LunarLander-v2")

eposides = 10
for eq in range(eposides):
    obs = env.reset()
    done = False
    rewards = 0
    while not done:
        action = env.action_space.sample()
        obs, reward, done, info = env.step(action)
        env.render()
        rewards += reward
    print(rewards)

随机初始化，视频链接：lunar_lander_random