SportsNGEN: Sustained Generation of Realistic Multi-player Sports Gameplay
This work addresses the need for accurate sports simulations to inform coaching decisions and enhance broadcast coverage, though it is incremental as it applies existing transformer methods to sports data.
The paper tackles the problem of simulating realistic multi-player sports gameplay by developing SportsNGEN, a transformer-based engine trained on tracking data, which generates sustained tennis matches and predicts rally outcomes, shot choices, and counterfactual scenarios, with evaluation showing it is probabilistically well-calibrated to real match statistics.
We present a transformer decoder based sports simulation engine, SportsNGEN, trained on sports player and ball tracking sequences, that is capable of generating sustained gameplay and accurately mimicking the decision making of real players. By training on a large database of professional tennis tracking data, we demonstrate that simulations produced by SportsNGEN can be used to predict the outcomes of rallies, determine the best shot choices at any point, and evaluate counterfactual or what if scenarios to inform coaching decisions and elevate broadcast coverage. By combining the generated simulations with a shot classifier and logic to start and end rallies, the system is capable of simulating an entire tennis match. We evaluate SportsNGEN by comparing statistics of the simulations with those of real matches between the same players. We show that the model output sampling parameters are crucial to simulation realism and that SportsNGEN is probabilistically well-calibrated to real data. In addition, a generic version of SportsNGEN can be customized to a specific player by fine-tuning on the subset of match data that includes that player. Finally, we show qualitative results indicating the same approach works for football.