Planning under Distribution Shifts with Causal POMDPs
📖 Full Retelling
arXiv:2602.23545v1 Announce Type: new
Abstract: In the real world, planning is often challenged by distribution shifts. As such, a model of the environment obtained under one set of conditions may no longer remain valid as the distribution of states or the environment dynamics change, which in turn causes previously learned strategies to fail. In this work, we propose a theoretical framework for planning under partial observability using Partially Observable Markov Decision Processes (POMDPs) f
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
--> Computer Science > Artificial Intelligence arXiv:2602.23545 [Submitted on 26 Feb 2026] Title: Planning under Distribution Shifts with Causal POMDPs Authors: Matteo Ceriscioli , Karthika Mohan View a PDF of the paper titled Planning under Distribution Shifts with Causal POMDPs, by Matteo Ceriscioli and 1 other authors View PDF HTML Abstract: In the real world, planning is often challenged by distribution shifts. As such, a model of the environment obtained under one set of conditions may no longer remain valid as the distribution of states or the environment dynamics change, which in turn causes previously learned strategies to fail. In this work, we propose a theoretical framework for planning under partial observability using Partially Observable Markov Decision Processes formulated using causal knowledge. By representing shifts in the environment as interventions on this causal POMDP, the framework enables evaluating plans under hypothesized changes and actively identifying which components of the environment have been altered. We show how to maintain and update a belief over both the latent state and the underlying domain, and we prove that the value function remains piecewise linear and convex in this augmented belief space. Preservation of PWLC under distribution shifts has the advantage of maintaining the tractability of planning via $\alpha$-vector-based POMDP methods. Comments: To appear at the 36th International Conference on Automated Planning and Scheduling (ICAPS-26) Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2602.23545 [cs.AI] (or arXiv:2602.23545v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2602.23545 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Matteo Ceriscioli [ view email ] [v1] Thu, 26 Feb 2026 23:00:13 UTC (25 KB) Full-text links: Access Paper: View a PDF of the paper titled Planning under Distribution Shifts with Causal POMDPs, by Matteo Ceriscioli and 1 other a...
Read full article at source