Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey

TL;DR

This survey explores how integrating Knowledge Representation and Reasoning (KRR) with Reinforcement Learning (RL) can address challenges like generalization, sample efficiency, safety, and interpretability in complex real-world problems.

Contribution

It provides an overview of recent efforts combining KRR with RL, highlighting the potential benefits and open challenges in this emerging research area.

Findings

KRR enhances RL's ability to incorporate high-level domain knowledge.

Integrating KRR can improve RL's sample efficiency and safety.

Open problems include scalable reasoning and knowledge integration in RL.

Abstract

Reinforcement Learning (RL) has achieved tremendous development in recent years, but still faces significant obstacles in addressing complex real-life problems due to the issues of poor system generalization, low sample efficiency as well as safety and interpretability concerns. The core reason underlying such dilemmas can be attributed to the fact that most of the work has focused on the computational aspect of value functions or policies using a representational model to describe atomic components of rewards, states and actions etc, thus neglecting the rich high-level declarative domain knowledge of facts, relations and rules that can be either provided a priori or acquired through reasoning over time. Recently, there has been a rapidly growing interest in the use of Knowledge Representation and Reasoning (KRR) methods, usually using logical languages, to enable more abstract representation and efficient learning in RL. In this survey, we provide a preliminary overview on these endeavors that leverage the strengths of KRR to help solving various problems in RL, and discuss the challenging open problems and possible directions for future work in this area.