Google Research Football: A Novel Reinforcement Learning Environment

Abstract

Recent progress in the field of reinforcement learning has been accelerated by virtual learning environments such as video games, where novel algorithms and ideas can be quickly tested in a safe and reproducible manner. We introduce the Google Research Football Environment, a new reinforcement learning environment where agents are trained to play football in an advanced, physics-based 3D simulator. The resulting environment is challenging, easy to use and customize, and it is available under a permissive open-source license. In addition, it provides support for multiplayer and multi-agent experiments. We propose three full-game scenarios of varying difficulty with the Football Benchmarks and report baseline results for three commonly used reinforcement algorithms (IMPALA, PPO, and Ape-X DQN). We also provide a diverse set of simpler scenarios with the Football Academy and showcase several promising research directions.

Stats

• citations197
• S2 citations—
• github stars0
• HF likes0
• heat score17.22
• arxiv keykurach2019google

Related papers

• Boosting Studies Of Multi-agent Reinforcement Learning On Google Research Football Environment: The Past, Present, And Future (2023)4.52
• An Empirical Study On Google Research Football Multi-agent Scenarios (2023)6.77
• 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
• Rsoccer: A Framework For Studying Reinforcement Learning In Small And Very Small Size Robot Soccer (2021)8.35
• Graph Neural Network Based Agent In Google Research Football (2022)0.00
• DIAMBRA Arena: A New Reinforcement Learning Platform For Research And Experimentation (2022)0.00
• Eden: A Unified Environment Framework For Booming Reinforcement Learning Algorithms (2021)0.00