Paper ID: 2403.12977

SportsNGEN: Sustained Generation of Multi-player Sports Gameplay

Lachlan Thorpe, Lewis Bawden, Karanjot Vendal, John Bronskill, Richard E. Turner

We present a transformer decoder based model, SportsNGEN, that is trained on sports player and ball tracking sequences that is capable of generating realistic and sustained gameplay. We train and evaluate SportsNGEN on a large database of professional tennis tracking data and demonstrate that 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. In addition, a generic version of SportsNGEN can be customized to a specific player by fine-tuning on match data that includes that player. We show that our model is well calibrated and can be used to derive insights for coaches and broadcasters by evaluating counterfactual or what if options. Finally, we show qualitative results indicating the same approach works for football.

Submitted: Feb 10, 2024