This is a gym version of various games for reinforcenment learning.
Project description
# Gym Games
This is a gym compatible version of various games for reinforcenment learning.
For [PyGame Learning Environment](https://pygame-learning-environment.readthedocs.io/en/latest/user/games.html), the default observation is a non-visual state representation of the game.
For [MinAtar](https://github.com/kenjyoung/MinAtar), the default observation is a visual input of the game.
## Environments
PyGame learning environment: - Catcher-PLE-v0 - FlappyBird-PLE-v0 - Pixelcopter-PLE-v0 - PuckWorld-PLE-v0 - Pong-PLE-v0
MinAtar: - Asterix-MinAtar-v0 - Breakout-MinAtar-v0 - Freeway-MinAtar-v0 - Seaquest-MinAtar-v0 - Space_invaders-MinAtar-v0
## Installation
### Gym
Please read the instruction [here](https://github.com/openai/gym).
### Pygame
On OSX:
brew install sdl sdl_ttf sdl_image sdl_mixer portmidi pip install pygame
On Ubuntu:
sudo apt-get -y install python-pygame pip install pygame
Others: Please read the instruction [here](http://www.pygame.org/wiki/GettingStarted#Pygame%20Installation).
### PyGame Learning Environment
pip install git+https://github.com/ntasfi/PyGame-Learning-Environment.git
## MinAtar
pip install git+https://github.com/kenjyoung/MinAtar.git
### Gym-games
Install from source:
pip install git+https://github.com/qlan3/gym-games.git
Install from PyPi:
pip install gym-games
## Example
Run python test.py.
## Cite
Please use this bibtex to cite this repo:
@misc{gym-games, author = {Qingfeng, Lan}, title = {Gym Compatible Games for Reinforcenment Learning}, year = {2019}, publisher = {GitHub}, journal = {GitHub Repository}, howpublished = {url{https://github.com/qlan3/gym-games}} }
## References
[gym-ple](https://github.com/lusob/gym-ple)
[MinAtar](https://github.com/kenjyoung/MinAtar)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for gym_games-1.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c263e688eb0983019e269b976be82412456474f6a5c971ec5d4ef1e00ccbaaf1 |
|
MD5 | 3f1b6e1e39fda39a44d7a3f23779df9f |
|
BLAKE2b-256 | 46474eb6bd70bdcfe2f8689d78bd95bdd458d40c2f5b5dc3c6668f49e1be5604 |