# Planning under Distribution Shifts with Causal POMDPs

arXiv: https://arxiv.org/abs/2602.23545 · HTML: https://mlsanity.com/paper/2602.23545/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [Robust agents learn causal world models](https://mlsanity.com/paper/2402.10877/) (2024)
- [Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution](https://mlsanity.com/paper/1801.04016/) (2018)
- [Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning](https://mlsanity.com/paper/2010.03110/) (2020)
- [Agent Incentives: A Causal Perspective](https://mlsanity.com/paper/2102.01685/) (2021)
- [A Bayesian Approach to Learning Causal Networks](https://mlsanity.com/paper/1302.4958/) (2013)
- [CAR-DESPOT: Causally-Informed Online POMDP Planning for Robots in Confounded Environments](https://mlsanity.com/paper/2304.06848/) (2023)

## Abstract (arXiv)

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.