A Reinforcement Learning Based Approach to Play Calling in Football
This work addresses decision-making in sports analytics for football teams and analysts, but it appears incremental as it applies established theory to a specific domain.
The paper tackles the problem of optimizing play calling in football by using reinforcement learning to maximize expected utility based on outcome probabilities and terminal utilities derived from game data, resulting in optimized single-play decision choices.
With the vast amount of data collected on football and the growth of computing abilities, many games involving decision choices can be optimized. The underlying rule is the maximization of an expected utility of outcomes and the law of large numbers. The data available allows us to compute with high accuracy the probabilities of outcomes of decisions and the well defined points system in the game allows us to have the necessary terminal utilities. With some well established theory we can then optimize choices at a single play level.