Online Competitive Information Gathering for Partially Observable Trajectory Games

TL;DR

This paper introduces an online method for rational trajectory planning in partially observable stochastic games, enabling game-theoretic agents to actively gather information in continuous environments efficiently.

Contribution

It formulates a finite horizon refinement of POSGs and develops an online particle-based approach for trajectory planning with stochastic gradient play, suitable for complex continuous scenarios.

Findings

Demonstrates active information gathering in pursuit-evasion and warehouse scenarios.

Outperforms passive strategies in continuous environments.

Extends to multi-player and obstacle-rich settings.

Abstract

Game-theoretic agents must make plans that optimally gather information about their opponents. These problems are modeled by partially observable stochastic games (POSGs), but planning in fully continuous POSGs is intractable without heavy offline computation or assumptions on the order of belief maintained by each player. We formulate a finite history/horizon refinement of POSGs which admits competitive information gathering behavior in trajectory space, and through a series of approximations, we present an online method for computing rational trajectory plans in these games which leverages particle-based estimations of the joint state space and performs stochastic gradient play. We also provide the necessary adjustments required to deploy this method on individual agents. The method is tested in continuous pursuit-evasion and warehouse-pickup scenarios (alongside extensions to $N > 2$ players and to more complex environments with visual and physical obstacles), demonstrating evidence of active information gathering and outperforming passive competitors.