OpenRL/tizero

Introduction

Reinforcement learning agent for Google Research Football.

Code accompanying the paper "TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play" (AAMAS 2023).

[paper] [videos] [code]

Installation

• Follow the instructions in gfootball to set up the environment.
• pip install gfootball
• pip install tizero (or clone this repo and pip install -e .).
• test the installation by python3 -m gfootball.play_game --action_set=full.

Convert dump file to video

After the installation, you can use tizero to convert a dump file to a video file. The usage is tizero dump2video <dump_file> <output_dir> --episode_length <the length> --render_type <2d/3d>.

You can download an example dump file from here. And then execute tizero dump2video daily_6484285.dump ./ in your terminal. By default, the episode length is 3000 and the render type is 2d. Wait a minute, you will get a video file named daily_6484285.avi in your current directory.

Submit TiZero to JIDI(及第评测平台)

JIDI is a public evaluation platform for RL agents. You can submit your agent of GRF at: http://www.jidiai.cn/env_detail?envid=34.

You can submit this agent to JIDI directly.

Cite

Please cite our paper if you use our codes or our weights in your own work:

@article{lin2023tizero,
  title={TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play},
  author={Lin, Fanqi and Huang, Shiyu and Pearce, Tim and Chen, Wenze and Tu, Wei-Wei},
  journal={arXiv preprint arXiv:2302.07515},
  year={2023}
}