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

TL;DR

This paper introduces a decentralized sequential generative modeling approach for multi-agent behavior prediction that incorporates partial observations and mechanical constraints, improving biological plausibility and interpretability.

Contribution

It presents a novel hierarchical variational recurrent neural network framework for multi-agent imitation learning with partial data and biomechanical constraints.

Findings

Effective in reducing constraint violations

Accurate long-term trajectory prediction

Realistic multi-agent behavior simulation

Abstract

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.