{"type":"ScholarlyArticle","title":"Solving Partially Observable Stochastic Shortest-Path Games","authors":[{"name":"Petr Tomášek","slug":"petr-tomasek","given":"Petr","family":"Tomášek","affiliation":""},{"name":"Karel Horák","slug":"karel-horak","given":"Karel","family":"Horák","affiliation":""},{"name":"Aditya Aradhye","slug":"aditya-aradhye","given":"Aditya","family":"Aradhye","affiliation":""},{"name":"Branislav Bošanský","slug":"branislav-bosansky","given":"Branislav","family":"Bošanský","affiliation":""},{"name":"Krishnendu Chatterjee","slug":"krishnendu-chatterjee","given":"Krishnendu","family":"Chatterjee","affiliation":""}],"abstract":"We study the two-player zero-sum extension of the partially observable stochastic shortest-path problem where one agent has only partial information about the environment.\r\nWe formulate this problem as a partially observable stochastic game (POSG): given a set of target states and negative rewards for each transition, the player with imperfect information maximizes the expected undiscounted total reward until a target state is reached. The second player with the perfect information aims for the opposite. \r\nWe base our formalism on POSGs with one-sided observability (OS-POSGs) and give the following contributions:\r\n(1) we introduce a novel heuristic search value iteration algorithm that iteratively solves depth-limited variants of the game,\r\n(2) we derive the bound on the depth guaranteeing an arbitrary precision, (3) we propose a novel upper-bound estimation that allows early terminations, and\r\n(4) we experimentally evaluate the algorithm on a pursuit-evasion game.","doi":"10.24963/ijcai.2021/575","url":"https://ijcai.org/proceedings/2021/575","pdf":"https://ijcai.org/proceedings/2021/0575.pdf","markdown":"https://ijcai.org/proceedings/2021/575.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/575","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Planning and Scheduling","track":"Main Track","number":575,"pages":{"first":4182,"last":4189},"keywords":["Uncertainty in AI: Sequential Decision Making","Agent-based and Multi-agent Systems: Noncooperative Games","Planning and Scheduling: Planning with Incomplete Information"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}