Planning Under Distribution Shifts with Causal POMDPs
Proceedings of the International Conference on Automated Planning and Scheduling · 08.06.2026 · 36 (1) · 367-371
DOI: 10.1609/icaps.v36i1.42847 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the International Conference on Automated Planning and Scheduling, online erschienen am 08.06.2026. Verfasst von Matteo Ceriscioli und 1 weiteren Autor:innen.
Abstract (Originalsprache)
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) 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 (PWLC) in this augmented belief space. Preservation of PWLC under distribution shifts has the advantage of maintaining the tractability of planning via α-vector-based POMDP methods.
Zitieren
APA
Ceriscioli, M., & Mohan, K. (2026). Planning Under Distribution Shifts with Causal POMDPs. Proceedings of the International Conference on Automated Planning and Scheduling, 36(1), 367-371. https://doi.org/10.1609/icaps.v36i1.42847
Vancouver
Ceriscioli M, Mohan K. Planning Under Distribution Shifts with Causal POMDPs. Proceedings of the International Conference on Automated Planning and Scheduling. 2026;36(1):367-371. doi:10.1609/icaps.v36i1.42847
BibTeX
@article{Ceriscioli2026,
author = {Ceriscioli, Matteo and Mohan, Karthika},
title = {Planning Under Distribution Shifts with Causal POMDPs},
journal = {Proceedings of the International Conference on Automated Planning and Scheduling},
year = {2026},
volume = {36},
number = {1},
pages = {367--371},
doi = {10.1609/icaps.v36i1.42847}
}
EUVIMED