arXiv (Cornell University) · 2013 · 148 citations · 22 references
BusinessDecision SciencesAlgorithmsMarkov Decision ProcessesStochastic ProcessesConstrained Markov Decision ProcessesFinite-state MachinesOptimal ControlPartially Observable Markov Decision ProcessesReinforcement LearningStochastic ControlDeterministic Policy SearchFinite Automata TheoryFinite-horizon Decision MakingGradient Method OptimizationOptimal PoliciesPolicy Search For PomdpsPomdp SolversStochastic Policy Search
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 results with a branch-and-bound method for finding globally optimal deterministic policies, and a gradient-ascent method for finding locally optimal stochastic policies.
22
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations