Skip to content

An OpenAI Gym interface to a Tetris clone.

License

Notifications You must be signed in to change notification settings

Olloxan/gym-tetris

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

gym-Tetris

PackageVersion PythonVersion Stable Format License

An OpenAI Gym environment for Tetris. This environemnt derives from the Tetromino clone developed by Al Sweigart.

Tetris

Installation

The preferred installation of gym-tetris is from pip:

pip install gym-tetris

Usage

Python

You must import gym_tetris before trying to make an environment. This is because gym environments are registered at runtime.

import gym_tetris
env = gym_tetris.make('Tetris-v0')

done = True
for step in range(5000):
    if done:
        state = env.reset()
    state, reward, done, info = env.step(env.action_space.sample())

env.close()

NOTE: gym_tetris.make is just an alias to gym.make for convenience.

Command Line

gym_tetris feature a command line interface for playing environments using either the keyboard, or uniform random movement.

gym_tetris -e <the environment ID to play> -m <`human` or `random`>

NOTE: by default, -e is set to Tetris-v0 and -m is set to human.

Citation

Please cite gym-tetris if you use it in your research.

@misc{gym-tetris,
  author = {Albert Sweigart and Christian Kauten},
  title = {{Tetris} for {OpenAI Gym}},
  year = {2018},
  publisher = {GitHub},
  howpublished = {\url{https://github.com/Kautenja/gym-tetris}},
}

action: 0: none 1: move left
2: move right
3: move down
4: rotate left 5: rotate right 6: move left+down 7: move right+down 8: mode left, rotate left 9: move right, rotate right 10: move right, rotate left 11: move left, rotate right

About

An OpenAI Gym interface to a Tetris clone.

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 81.3%
  • Jupyter Notebook 18.3%
  • Makefile 0.4%