Optimizing Fantasy Sports Team Selection with Deep Reinforcement Learning

Published in CODS-COMAD '24, Association for Computing Machinery, 2024

Formulates fantasy-sports team selection as a sequential decision problem under budget and lineup constraints, trains a deep RL policy on historical match outcomes, and benchmarks against greedy and integer-programming baselines. The learned policy surfaces lineup combinations that conventional optimizers miss because it can reason about correlated performance across players in the same match.

Recommended citation: Patil, N. et al. (2024). Optimizing Fantasy Sports Team Selection with Deep Reinforcement Learning. Proceedings of CODS-COMAD '24, ACM, 284–291.
Download Paper