Gobigger Explore Save

Still struggling with the high threshold or looking for the appropriate baseline? Come here and new starters can also play with your own multi-agents!

Project README

GoBigger-Explore

banner

EN

GoBigger-Explore is an open source code collection in the article "GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation" of ICLR 2023.

amazing balls

Outline

:rocket: Release Version

The current version is the latest version 0.4.0.

:point_down: Getting Start

System environment

  • Core 32
  • GPU (>=16G)
  • Memory 40G

Install the necessary package

git clone git/repo/path
cd bigger_rl
pip install -e .

Start training

  1. Serial Training(DQN、PPO、MAPPO、QMix、VMix、COMA)
  • Train
    python -u -m bigrl.bin.serial_train  --config abs/config/path
    
  • Evaluation
    python -u -m bigrl.bin.serial_eval  --config abs/config/path
    
  1. Parallel Training(IMPALA + Alphastar_Loss + League Training)
  • Train && Evaluation
    python -u -m bigrl.single.worker.trainer.trainer  --config abs/config/path
    

Results

  • RL Agent vs Bot (Without cooperation)
  • Bot vs Bot
  • RL Agent vs Bot (With cooperation)

:heart_eyes: Resources

:star: Join and Contribute

Welcome to OpenDI Lab GoBigger community! Scan the QR code and add us on Wechat:

QR code

Or you can contact us with slack or email ([email protected]).

:cocktail: License

GoBigger-Explore released under the Apache 2.0 license.

Open Source Agenda is not affiliated with "Gobigger Explore" Project. README Source: opendilab/Gobigger-Explore
Stars
169
Open Issues
1
Last Commit
1 year ago
License

Open Source Agenda Badge

Open Source Agenda Rating