Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling

• Published in: arXiv.org
• Main Authors: Fujii, Keisuke, Takeishi, Naoya, Kawahara, Yoshinobu, Takeda, Kazuya
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 01.12.2023
• Subjects: Biological weapons; Biomechanics; Computer Science - Learning; Computer Science - Multiagent Systems; Constraint modelling; Empirical analysis; Learning; Multiagent systems; Recurrent neural networks; Soccer; Statistics - Machine Learning
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2007.03155

Extracting the rules of real-world multi-agent behaviors is a current challenge in various scientific and engineering fields. Biological agents independently have limited observation and mechanical constraints; however, most of the conventional data-driven models ignore such assumptions, resulting in lack of biological plausibility and model interpretability for behavioral analyses. Here we propose sequential generative models with partial observation and mechanical constraints in a decentralized manner, which can model agents' cognition and body dynamics, and predict biologically plausible behaviors. We formulate this as a decentralized multi-agent imitation-learning problem, leveraging binary partial observation and decentralized policy models based on hierarchical variational recurrent neural networks with physical and biomechanical penalties. Using real-world basketball and soccer datasets, we show the effectiveness of our method in terms of the constraint violations, long-term trajectory prediction, and partial observation. Our approach can be used as a multi-agent simulator to generate realistic trajectories using real-world data.