Online Competitive Information Gathering for Partially Observable Trajectory Games

When planning a trajectory through continuous space, a rational agent should consider the information limitations of itself and its counterparts, and seek out useful observations. While approximate solutions can be found to many such partially observable multi-agent problems (i.e., through reinforcement learning), doing so online and in continuous spaces is not trivial. The existing control-theoretic method of model predictive game play (MPGP) combines continuous, online control with game theoretic rational play, but does not inherently support partial observability. Our work addresses this case, presenting a method to generate informationaware plans with MPGP alongside adjustments required to deploy it on individual interacting agents. While our method is not real-time, it allows us to consider what is required to compute solutions from scratch. We evaluate the method in variants of a partially observable pursuit-evasion game, and demonstrate evidence of information gathering behavior that outperforms passive competitors.