{"type":"ScholarlyArticle","title":"Partially Observable Reference Policy Programming","authors":[{"name":"Edward Kim","slug":"edward-kim","given":"Edward","family":"Kim","affiliation":""},{"name":"Hanna Kurniawati","slug":"hanna-kurniawati","given":"Hanna","family":"Kurniawati","affiliation":""}],"abstract":"This paper proposes Partially Observable Reference Policy Programming, a novel anytime online approximate POMDP solver which samples meaningful future histories very deeply while simultaneously forcing a gradual policy update. We provide theoretical guarantees for the algorithm’s underlying scheme which say that the performance loss is bounded by the average of the sampling approximation errors rather than the usual maximum; a crucial requirement given the sampling sparsity of online planning. Empirical evaluations on two large-scale problems with dynamically evolving environments—including a helicopter emergency scenario in the Corsica region requiring approximately 150 planning steps—corroborate the theoretical results and indicate that our solver considerably outperforms current online benchmarks.","doi":"10.24963/ijcai.2025/949","url":"https://ijcai.org/proceedings/2025/949","pdf":"https://ijcai.org/proceedings/2025/0949.pdf","markdown":"https://ijcai.org/proceedings/2025/949.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/949","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Planning and Scheduling","track":"Main Track","number":949,"pages":{"first":8536,"last":8543},"keywords":["Planning and Scheduling: PS: Planning under uncertainty","Planning and Scheduling: PS: Planning with Incomplete Information","Machine Learning: ML: Partially observable reinforcement learning and POMDPs","Planning and Scheduling: PS: POMDPs"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}