Solving POMDPs by Searching the Space of Finite Policies [article]

Nicolas Meuleau, Kee-Eung Kim, Leslie Pack Kaelbling, Anthony R. Cassandra
2013 arXiv   pre-print
Solving partially observable Markov decision processes (POMDPs) is highly intractable in general, at least in part because the optimal policy may be infinitely large. In this paper, we explore the problem of finding the optimal policy from a restricted set of policies, represented as finite state automata of a given size. This problem is also intractable, but we show that the complexity can be greatly reduced when the POMDP and/or policy are further constrained. We demonstrate good empirical
more » ... ults with a branch-and-bound method for finding globally optimal deterministic policies, and a gradient-ascent method for finding locally optimal stochastic policies.
arXiv:1301.6720v1 fatcat:rq2dryw4frfxba3hkb2chu42k4