Deciding What is Good-for-MDPs

Abstract

Nondeterministic Good-for-MDP (GFM) automata are for MDP model checking and reinforcement learning what good-for-games automata are for synthesis: a more compact alternative to deterministic automata that displays nondeterminism, but only so much that it can be resolved locally, such that a syntactic product can be analysed. GFM has recently been introduced as a property for reinforcement learning, where the simpler Büchi acceptance conditions it allows to use is key. However, while there are classic and novel techniques to obtain automata that are GFM, there has not been a decision procedure for checking whether or not an automaton is GFM. We show that GFM-ness is decidable and provide an EXPTIME decision procedure as well as a PSPACE-hardness proof. ACM Subject ClassificationTheory of computation → Automata over infinite objects; Mathematics of computing → Markov processes