Good-for-MDPs Automata for Probabilistic Analysis and Reinforcement Learning

Ernst Moritz Hahn, Mateo Perez, Fabio Somenzi +3

We characterize the class of nondeterministic $\omega$-automata that can be used for the analysis of finite Markov decision processes (MDPs). We call these automata `good-for-MDPs' (GFM…