Entropy Maximization for Partially Observable Markov Decision Processes

We study the problem of synthesizing a controller that maximizes the entropy of a partially observable Markov decision process (POMDP) subject to a constraint on the expected total reward. Such a controller minimizes the predictability of an agent’s trajectories to an outside observer while guaranteeing the completion of a task expressed by a reward function. Focusing on finite-state controllers (FSCs) with deterministic memory transitions, we show that the maximum entropy of a POMDP is lower bounded by the maximum entropy of the parameteric Markov chain (pMC) induced by such FSCs. This relationship allows us to recast the entropy maximization problem as a so-called parameter synthesis problem for the induced pMC. We then present an algorithm to synthesize an FSC that locally maximizes the entropy of a POMDP over FSCs with the same number of memory states. In a numerical example, we highlight the benefit of using an entropy-maximizing FSC compared with an FSC that simply finds a feasible policy for accomplishing a task.