Reinforcement Learning with Limited Reinforcement: Using Bayes Risk for Active Learning in POMDPs.

Abstract

Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that increase an agent's reward. Unfortunately, most POMDPs are defined with a large number of parameters which are difficult to specify only from domain knowledge. In this paper, we present an approximation approach that allows us to treat the POMDP model parameters as additional hidden state in a "model-uncertainty" POMDP. Coupled with model-directed queries, our planner actively learns good policies. We demonstrate our approach on several POMDP problems.