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.
JAIR 58, 231–266 (2017)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
VOiLA learns task-agnostic POMDP models with diffusion models, distills them for speed, and integrates with vectorized online planning to match or exceed baselines using under 10% of the training data while generalizing better and succeeding on physical robots.
citing papers explorer
-
VOiLA: Vectorized Online Planning with Learned Diffusion Model for POMDP Agents
VOiLA learns task-agnostic POMDP models with diffusion models, distills them for speed, and integrates with vectorized online planning to match or exceed baselines using under 10% of the training data while generalizing better and succeeding on physical robots.