Search Machine Learning Repository:
Average Reward Optimization Objective In Partially Observable Domains
Authors: Yuri Grinberg and Doina Precup
Conference: Proceedings of the 30th International Conference on Machine Learning (ICML-13)
Abstract: We consider the problem of average reward optimization in domains with partial observability, within the modeling framework of linear predictive state representations (PSRs). The key to average-reward computation is to have a well-defined stationary behavior of a system, so the required averages can be computed. If, additionally, the stationary behavior varies smoothly with changes in policy parameters, average-reward control through policy search also becomes a possibility. In this paper, we show that PSRs have a well-behaved stationary distribution, which is a rational function of policy parameters. Based on this result, we define a related reward process particularly suitable for average reward optimization, and analyze its properties. We show that in such a predictive state reward process, the average reward is a rational function of the policy parameters, whose complexity depends on the dimension of the underlying linear PSR. This result suggests that average reward-based policy search methods can be effective when the dimension of the system is small, even when the system representation in the POMDP framework requires many hidden states. We provide illustrative examples of this type.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).