[PYTHON] Reinforcement learning 37 Make an automatic start with Atari's wrapper

It is intended for AI beginners from junior high school students to university students.

When trying to use OpenAI's ATARI, I want a wrapper to cover the peculiarities of the game. For example, in Breakout, the life point is initially set to 5, but the game will not work unless you press the fire button at the beginning and when the life point decreases (when it fails). If you do not exceed this, it will be like a fool that machine learning will not progress at all. Personally, it's a waste of time. In the first place, a wrapper called FireResetEnv is prepared, but if you break a block, it will not move every time your life decreases, so if you fail once, it will remain as it is. So I wrote a wrapper like the one below.

class FireResetEnvAuto(gym.Wrapper):
    def __init__(self, env):
        """Take action on reset for envs that are fixed until firing."""
        gym.Wrapper.__init__(self, env)
        assert env.unwrapped.get_action_meanings()[1] == 'FIRE'
        assert len(env.unwrapped.get_action_meanings()) >= 3
        self.lives = 0

    def reset(self, **kwargs):
        self.lives = self.env.unwrapped.ale.lives()
        obs, _, done, info = self.env.step(1)
        if done or info.get('needs_reset', False):
        obs, _, done, info = self.env.step(2)
        if done or info.get('needs_reset', False):
        return obs

    def step(self, ac):
        lives = self.env.unwrapped.ale.lives()
        if lives<self.lives:
            return self.env.step(1)
        return self.env.step(ac)

Most are chainerrl / wrapper / atari_wrapper.py I just added a little. This is chokozainerrl.

Recommended Posts

Reinforcement learning 37 Make an automatic start with Atari's wrapper
Play with reinforcement learning with MuZero
Reinforcement learning starting with Python
Reinforcement learning 34 Make continuous Agent videos
Reinforcement learning 13 Try Mountain_car with ChainerRL.
Make ASCII art with deep learning
Explore the maze with reinforcement learning
Make people smile with Deep Learning
Make Scrapy an exe with Pyinstaller
Make an audio interface controller with pyusb (1)
[Python] Easy Reinforcement Learning (DQN) with Keras-RL
Reinforcement learning 11 Try OpenAI acrobot with ChainerRL.
[Python] Make a game with Pyxel-Use an editor-
Make a monitoring device with an infrared sensor
See the behavior of drunkenness with reinforcement learning
[Reinforcement learning] Experience Replay is easy with cpprb!
Reinforcement learning 12 ChainerRL quick start guide windows version
Challenge block breaking with Actor-Critic model reinforcement learning
[Mac] I tried reinforcement learning with OpenAI Baselines
[Learning memo] How to make an application with Django ~ Until Hello World is displayed ~
[Learning memo] How to make an application with Django ~ From virtual environment to pushing to github ~