Year: 2014
Type: article
Abstract: We introduce Multi-Environment Markov Decision Processes (MEMDPs) which are MDPs with a set of probabilistic transition functions. The goal in a MEMDP is to synthesize a single controller with guaranteed performances against all environments even though the environment is unknown a priori. While MEMDPs can be seen as a special class of partially observable MDPs, we show that several verification problems that are undecidable for partially observable MDPs, are decidable for MEMDPs and sometimes have even efficient solutions.
Parent work: LIPIcs, Volume 29, FSTTCS'14, Complete Volume
Authors: Raskin, Jean-Francois, Sankur, Ocan
Institution: Université Libre de Bruxelles
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1563302260
