Heterogeneous Knowledge for Augmented Modular Reinforcement Learning

arXiv:2306.01158v2 Announce Type: replace
Abstract: Existing modular Reinforcement Learning (RL) architectures are generally based on reusable components, also allowing for ``plug-and-play'' integration. However, these modules are homogeneous in nature - in fact, they essentially provide policies obtained via RL through the maximization of individual reward functions. Consequently, such solutions still lack the ability to integrate and process multiple types of information (i.e., heterogeneous knowledge representations), such as rules, sub-goals, and skills from various sources. In this paper, we discuss several …

abstract architectures arxiv components cs.ai cs.lg functions however integration knowledge modular modules nature policies reinforcement reinforcement learning solutions through type via