Reinforcement Learning with Non-Cumulative Objective

arXiv:2307.04957v2 Announce Type: replace
Abstract: In reinforcement learning, the objective is almost always defined as a \emph{cumulative} function over the rewards along the process. However, there are many optimal control and reinforcement learning problems in various application fields, especially in communications and networking, where the objectives are not naturally expressed as summations of the rewards. In this paper, we recognize the prevalence of non-cumulative objectives in various problems, and propose a modification to existing algorithms for optimizing such objectives. Specifically, …

abstract application arxiv communications control cs.ai cs.lg cs.ni fields function however math.oc networking process reinforcement reinforcement learning stat.ml type