PlayBest: Professional Basketball Player Behavior Synthesis via Planning with Diffusion

TL;DR

PlayBest introduces a diffusion-based model for synthesizing professional basketball player behaviors, enabling realistic and strategic trajectory generation that aligns with expert tactics by leveraging historical NBA data and reward-guided sampling.

Contribution

This work pioneers the application of diffusion probabilistic models to dynamic sports decision-making, integrating value functions for strategic trajectory synthesis in basketball.

Findings

Generated trajectories resemble professional plays

Model captures complex on-court dynamics

Synthesized strategies align with expert tactics

Abstract

Dynamically planning in complex systems has been explored to improve decision-making in various domains. Professional basketball serves as a compelling example of a dynamic spatio-temporal game, encompassing context-dependent decision-making. However, processing the diverse on-court signals and navigating the vast space of potential actions and outcomes make it difficult for existing approaches to swiftly identify optimal strategies in response to evolving circumstances. In this study, we formulate the sequential decision-making process as a conditional trajectory generation process. Based on the formulation, we introduce PlayBest (PLAYer BEhavior SynThesis), a method to improve player decision-making. We extend the diffusion probabilistic model to learn challenging environmental dynamics from historical National Basketball Association (NBA) player motion tracking data. To incorporate data-driven strategies, an auxiliary value function is trained with corresponding rewards. To accomplish reward-guided trajectory generation, we condition the diffusion model on the value function via classifier-guided sampling. We validate the effectiveness of PlayBest through simulation studies, contrasting the generated trajectories with those employed by professional basketball teams. Our results reveal that the model excels at generating reasonable basketball trajectories that produce efficient plays. Moreover, the synthesized play strategies exhibit an alignment with professional tactics, highlighting the model's capacity to capture the intricate dynamics of basketball games.