SportsNGEN: Sustained Generation of Realistic Multi-Player Sports Gameplay

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

2024

Abstract

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.

Paper Citation

in Harvard Style

Thorpe L., Bawden L., Vendal K., Bronskill J. and Turner R. (2024). SportsNGEN: Sustained Generation of Realistic Multi-Player Sports Gameplay. In Proceedings of the 12th International Conference on Sport Sciences Research and Technology Support - Volume 1: icSPORTS; ISBN 978-989-758-719-1, SciTePress, pages 119-130. DOI: 10.5220/0012892000003828

in Bibtex Style

@conference{icsports24,
author={Lachlan Thorpe and Lewis Bawden and Karanjot Vendal and John Bronskill and Richard Turner},
title={SportsNGEN: Sustained Generation of Realistic Multi-Player Sports Gameplay},
booktitle={Proceedings of the 12th International Conference on Sport Sciences Research and Technology Support - Volume 1: icSPORTS},
year={2024},
pages={119-130},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012892000003828},
isbn={978-989-758-719-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Sport Sciences Research and Technology Support - Volume 1: icSPORTS
TI - SportsNGEN: Sustained Generation of Realistic Multi-Player Sports Gameplay
SN - 978-989-758-719-1
AU - Thorpe L.
AU - Bawden L.
AU - Vendal K.
AU - Bronskill J.
AU - Turner R.
PY - 2024
SP - 119
EP - 130
DO - 10.5220/0012892000003828
PB - SciTePress