使用openai提供的gym运行montezuma‘s revenge强化学习环境

conda create -n atari python=3.8
conda activate atari
pip install opencv-python
pip install "gym[atari, accept-rom-license]"
pip install pyglet
pip install ale-py

import gym

env = gym.make("ALE/MontezumaRevenge-v5", render_mode='human')
env.action_space.seed(42)

observation, info = env.reset(seed=42)

for _ in range(1000):
    observation, reward, terminated, truncated, info = env.step(env.action_space.sample())

    if terminated or truncated:
        observation, info = env.reset()

env.close()

"""
env.action_space: Discrete(18)
env.observation_space: Box(0, 255, (210, 160, 3), uint8)
Env.reward_range: (-inf, inf)

"""

gym的版本问题以及运行不同游戏会出的具体问题各不相同，实在麻烦。。。