Generating Turn-Based Player Behavior via Experience from Demonstrations

Abstract

Turn-based sports, such as badminton and tennis, present challenges for imitating human player behaviors from offline datasets in sports analytics. We propose RallyNet, a novel hierarchical offline imitation learning model for turn-based player behaviors. RallyNet captures players' decision dependencies by modeling decision-making processes in turn-based sports as a contextual Markov decision process (CMDP). It leverages experience to generate contexts that aid decision-making, reducing errors. Additionally, RallyNet models player interactions using a latent geometric Brownian motion, enhancing realism and introducing helpful inductive bias. Experimental results on a real-world badminton game dataset demonstrate the effectiveness of RallyNet, outperforming prior offline imitation learning approaches and a state-of-the-art turn-based supervised method.