AI RESEARCH
Robustness Analysis of POMDP Policies to Observation Perturbations
arXiv CS.AI
•
ArXi:2604.21256v1 Announce Type: new Policies for Partially Observable Marko Decision Processes (POMDPs) are often designed using a nominal system model. In practice, this model can deviate from the true system during deployment due to factors such as calibration drift or sensor degradation, leading to unexpected performance degradation. This work studies policy robustness against deviations in the POMDP observation model. We