Online Competitive Information Gathering for Partially Observable Trajectory Games
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913871284928512 |
|---|---|
| author | Krusniak, Mel Xu, Hang Palermo, Parker Laine, Forrest |
| author_facet | Krusniak, Mel Xu, Hang Palermo, Parker Laine, Forrest |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01927 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Online Competitive Information Gathering for Partially Observable Trajectory Games Krusniak, Mel Xu, Hang Palermo, Parker Laine, Forrest Computer Science and Game Theory Artificial Intelligence Multiagent Systems Robotics 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. |
| title | Online Competitive Information Gathering for Partially Observable Trajectory Games |
| topic | Computer Science and Game Theory Artificial Intelligence Multiagent Systems Robotics |
| url | https://arxiv.org/abs/2506.01927 |