Race Strategy
Race strategy, encompassing optimal decision-making in competitive scenarios, aims to maximize performance by balancing competing objectives such as speed, fuel efficiency, and safety. Current research focuses on developing sophisticated simulation models, often employing reinforcement learning and model predictive control algorithms, to optimize strategies like pit stop timing and overtaking maneuvers in various racing contexts, from autonomous vehicles to motorsport. These advancements offer significant potential for improving performance in both simulated and real-world racing environments, and contribute to broader fields like optimization and control theory.
Papers
Explainable Reinforcement Learning for Formula One Race Strategy
Devin Thomas, Junqi Jiang, Avinash Kori, Aaron Russo, Steffen Winkler, Stuart Sale, Joseph McMillan, Francesco Belardinelli, Antonio Rago
Explainable Time Series Prediction of Tyre Energy in Formula One Race Strategy
Jamie Todd, Junqi Jiang, Aaron Russo, Steffen Winkler, Stuart Sale, Joseph McMillan, Antonio Rago