Song, Y; Jiang, H; Tian, Z; Zhang, H; Zhang, Y; Zhu, J; Dai, Z; ... Wang, J; + view all Song, Y; Jiang, H; Tian, Z; Zhang, H; Zhang, Y; Zhu, J; Dai, Z; Zhang, W; Wang, J; - view fewer (2024) An Empirical Study on Google Research Football Multi-agent Scenarios. Machine Intelligence Research , 21 pp. 549-570. 10.1007/s11633-023-1426-8.

Preview

Text 2305.09458.pdf - Other Download (4MB) | Preview

Abstract

Few multi-agent reinforcement learning (MARL) researches on Google research football (GRF) focus on the 11-vs-11 multi-agent full-game scenario and to the best of our knowledge, no open benchmark on this scenario has been released to the public. In this work, we fill the gap by providing a population-based MARL training pipeline and hyperparameter settings on multi-agent football scenario that outperforms the bot with difficulty 1.0 from scratch within 2 million steps. Our experiments serve as a reference for the expected performance of independent proximal policy optimization (IPPO), a state-of-the-art multi-agent reinforcement learning algorithm where each agent tries to maximize its own policy independently across various training configurations. Meanwhile, we release our training framework Light-MALib which extends the MALib codebase by distributed and asynchronous implementation with additional analytical tools for football games. Finally, we provide guidance for building strong football AI with population-based training and release diverse pretrained policies for benchmarking. The goal is to provide the community with a head start for whoever experiment their works on GRF and a simple-to-use population-based training framework for further improving their agents through self-play. The implementation is available at https://github.com/Shanghai-Digital-Brain-Laboratory/DB-Football .

Download activity - last month

Export as CSVJSONXML

Download activity - last 12 months

Export as XMLJSONCSV

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item