Online Competitive Information Gathering for Partially Observable Trajectory Games
This addresses the challenge of intractable planning in continuous partially observable games for agents needing competitive information gathering, though it is incremental as it builds on existing POSG frameworks with approximations.
The paper tackles the problem of planning for game-theoretic agents in partially observable stochastic games by formulating a finite refinement and developing an online method using particle-based estimations and stochastic gradient play, demonstrating active information gathering and outperforming passive competitors in continuous pursuit-evasion and warehouse-pickup scenarios.
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.