Effective Reinforcement Learning Based on Structural Information Principles

arXiv:2404.09760v1 Announce Type: new
Abstract: Although Reinforcement Learning (RL) algorithms acquire sequential behavioral patterns through interactions with the environment, their effectiveness in noisy and high-dimensional scenarios typically relies on specific structural priors. In this paper, we propose a novel and general Structural Information principles-based framework for effective Decision-Making, namely SIDM, approached from an information-theoretic perspective. This paper presents a specific unsupervised partitioning method that forms vertex communities in the state and action spaces based on their feature similarities. An aggregation …

abstract algorithms arxiv cs.ai cs.lg decision environment framework general information interactions making novel paper patterns reinforcement reinforcement learning the environment through type