Generating Multi-Agent Trajectories using Programmatic Weak Supervision

TL;DR

This paper introduces a hierarchical generative framework for modeling multi-agent trajectories, like basketball gameplay, using programmatic weak supervision to capture long-term coordination and high-level semantics.

Contribution

It extends programmatic weak supervision to spatiotemporal data and demonstrates its effectiveness in modeling complex multi-agent interactions in sports.

Findings

Successfully models long-term multi-agent coordination

Generates realistic basketball trajectories

Outperforms baseline models in evaluations

Abstract

We study the problem of training sequential generative models for capturing coordinated multi-agent trajectory behavior, such as offensive basketball gameplay. When modeling such settings, it is often beneficial to design hierarchical models that can capture long-term coordination using intermediate variables. Furthermore, these intermediate variables should capture interesting high-level behavioral semantics in an interpretable and manipulatable way. We present a hierarchical framework that can effectively learn such sequential generative models. Our approach is inspired by recent work on leveraging programmatically produced weak labels, which we extend to the spatiotemporal regime. In addition to synthetic settings, we show how to instantiate our framework to effectively model complex interactions between basketball players and generate realistic multi-agent trajectories of basketball gameplay over long time periods. We validate our approach using both quantitative and qualitative evaluations, including a user study comparison conducted with professional sports analysts.