AI RESEARCH
Data-driven robust Markov decision processes on Borel spaces: performance guarantees via an axiomatic approach
arXiv CS.LG
•
ArXi:2603.08979v1 Announce Type: cross We consider Marko decision processes (MDPs) with unknown disturbance distribution and address this problem using the robust Marko decision process (RMDP) approach. We construct the empirical distribution of the unknown disturbance distribution and characterize our ambiguity set of distributions as the sublevel set of a nonnegative distance function from the empirical distribution.