A Reinforcement Learning Badminton Environment for Simulating Player Tactics (Student Abstract)

Recent techniques for analyzing sports precisely has stimulated various approaches to improve player performance and fan engagement. However, existing are only able evaluate offline since testing in real-time matches requires exhaustive costs cannot be replicated. To test a safe reproducible simulator, we focus on turn-based introduce badminton environment by simulating rallies with different angles of view designing the states, actions, training procedures. This benefits not coaches players past tactic investigation, but also researchers from rapidly evaluating their novel algorithms. Our code is available at https://github.com/wywyWang/CoachAI-Projects/tree/main/Strategic%20Environment.