rho-POMDPs have Lipschitz-Continuous epsilon-Optimal Value Functions

Mathieu Fehr, Olivier Buffet, Vincent Thomas, Jilles Dibangoye

Neural Information Processing Systems 

Many state-of-the-art algorithms for solving Partially Observable Markov Decision Processes (POMDPs) rely on turning the problem into a "fully observable" problem--a belief MDP--and exploiting the piece-wise linearity and convexity

Similar Docs  Excel Report  more

TitleSimilaritySource
None found