Search papers, labs, and topics across Lattice.
ShuttleEnv, a new interactive reinforcement learning environment for badminton, is introduced, leveraging elite-player match data and probabilistic models to simulate rally dynamics. This data-driven approach allows for realistic agent-opponent interactions without physics-based simulation, enabling the training and analysis of diverse badminton strategies. The environment's interactive visualization allows users to explore different play styles and decision-making behaviors, demonstrating its potential for sports AI research.
Forget rigid physics engines, this badminton RL environment uses real player data to simulate realistic rallies and strategic gameplay.
We present ShuttleEnv, an interactive and data-driven simulation environment for badminton, designed to support reinforcement learning and strategic behavior analysis in fast-paced adversarial sports. The environment is grounded in elite-player match data and employs explicit probabilistic models to simulate rally-level dynamics, enabling realistic and interpretable agent-opponent interactions without relying on physics-based simulation. In this demonstration, we showcase multiple trained agents within ShuttleEnv and provide live, step-by-step visualization of badminton rallies, allowing attendees to explore different play styles, observe emergent strategies, and interactively analyze decision-making behaviors. ShuttleEnv serves as a reusable platform for research, visualization, and demonstration of intelligent agents in sports AI. Our ShuttleEnv demo video URL: https://drive.google.com/file/d/1hTR4P16U27H2O0-w316bR73pxE2ucczX/view
