Scalable Gradient Ascent for Controllers in Constrained POMDPs

摘要

This paper presents a novel gradient ascent al-gorithm and nonlinear programming algorithm for finite state controller policies in constrained partially observable Markov decision processes (CPOMDPs). A key component of the gradient ascent algorithm is a constraint projection to ensure constraints are satisfied. Both an optimal and an approximate projection are formally defined. A theoretical analysis of the algorithm and its projections is presented, formally proving aspects of projection correctness and algorithm convergence. Experiments evaluate the baseline and novel algorithms, as well as both constraint projections, on seven CPOMDP benchmark domains. The proposed novel algorithm is demonstrated on an actual robot performing a navigation task in a real household environment.