POMDP policies can be checked for robustness to observation model changes by solving a bi-level optimization via root-finding with the Robust Interval Search algorithm, which runs in polynomial time for non-sticky history-independent deviations when using finite-state controllers.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Non-parametric closed-form bounds on counterfactual MDP transitions across compatible causal models, supporting robust policy optimization under interval uncertainty.
citing papers explorer
-
Robustness Analysis of POMDP Policies to Observation Perturbations
POMDP policies can be checked for robustness to observation model changes by solving a bi-level optimization via root-finding with the Robust Interval Search algorithm, which runs in polynomial time for non-sticky history-independent deviations when using finite-state controllers.
-
Robust Counterfactual Inference in Markov Decision Processes
Non-parametric closed-form bounds on counterfactual MDP transitions across compatible causal models, supporting robust policy optimization under interval uncertainty.