Learning Explainable and Better Performing Representations of POMDP Strategies

arXiv:2401.07656v3 Announce Type: replace-cross
Abstract: Strategies for partially observable Markov decision processes (POMDP) typically require memory. One way to represent this memory is via automata. We present a method to learn an automaton representation of a strategy using a modification of the L*-algorithm. Compared to the tabular representation of a strategy, the resulting automaton is dramatically smaller and thus also more explainable. Moreover, in the learning process, our heuristics may even improve the strategy's performance. In contrast to approaches that …

abstract algorithm arxiv automaton cs.ai cs.lg cs.lo decision learn markov memory observable processes replace representation strategies strategy tabular type via