An Empirical Study On Google Research Football Multi-agent Scenarios

Abstract

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 f

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keysong2023an

Related papers

• Boosting Studies Of Multi-agent Reinforcement Learning On Google Research Football Environment: The Past, Present, And Future (2023)4.52
• Google Research Football: A Novel Reinforcement Learning Environment (2019)17.22
• Tikick: Towards Playing Multi-agent Football Full Games From Single-agent Demonstrations (2021)0.00
• Tizero: Mastering Multi-agent Football With Curriculum Learning And Self-play (2023)2.26
• Benchmarking Multi-agent Deep Reinforcement Learning Algorithms In Cooperative Tasks (2020)0.00
• Fightladder: A Benchmark For Competitive Multi-agent Reinforcement Learning (2024)0.00
• Fox: Formation-aware Exploration In Multi-agent Reinforcement Learning (2023)6.77
• Malib: A Parallel Framework For Population-based Multi-agent Reinforcement Learning (2021)0.00