arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.09458cs.LGcs.MA
收藏

Google Research Football 多智能体场景的实证研究

An Empirical Study on Google Research Football Multi-agent Scenarios

Institute of Automation, CAS(中国科学院自动化研究所);Digital Brain Lab(数字脑实验室);ShanghaiTech University(上海科技大学);Huawei Cloud(华为云);Shanghai Jiao Tong University(上海交通大学);University College London(伦敦大学学院)

Yan Song, He Jiang, Zheng Tian, Haifeng Zhang, Yingping Zhang, Jiangcheng Zhu, Zonghong Dai, Weinan Zhang, Jun Wang

AI总结:

本文针对 GRF 11v11 多智能体全场场景缺少开放基准的问题,提出基于种群的 MARL 训练流程与超参数设置,使 IPPO 在 200 万步内超越难度 1.0 机器人,并开源 Light-MALib 框架及预训练策略。

摘要:

关于 Google Research Football(GRF)的多智能体强化学习(MARL)研究很少关注 11v11 多智能体全场对战场景,并且据我们所知,目前尚未有面向公众发布的该场景开放基准。在本工作中,我们通过提供一种基于种群的多智能体 MARL 训练流程和超参数设置来填补这一空白,该方案在多智能体足球场景下能够在 200 万步内从零开始超越难度为 1.0 的内置机器人。我们的实验可作为独立近端策略优化(IPPO)预期性能的参考,IPPO 是一种先进的多智能体强化学习算法,其中每个智能体在各种训练配置下独立地最大化自身策略。同时,我们开源了训练框架 Light-MALib,它通过分布式和异步化实现扩展了 MALib 代码库,并增加了针对足球比赛的额外分析工具。最后,我们为基于种群训练构建强大的足球 AI 提供了指导,并发布了多样化的预训练策略用于基准测试。目标是让任何在 GRF 上进行实验的研究者都能获得先发优势,并提供一个简单易用的基于种群的训练框架,以便通过自博弈进一步改进其智能体。实现代码可在 https://github.com/Shanghai-Digital-Brain-Laboratory/DB-Football 获取。

英文摘要:

Few multi-agent reinforcement learning (MARL) research on Google Research Football (GRF) focus on the 11v11 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 open-source our training framework Light-MALib which extends the MALib codebase by distributed and asynchronized 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑