Causal Reinforcement Learning: A Survey

TL;DR

This survey reviews how integrating causality into reinforcement learning can improve understanding, generalization, and decision-making in complex, uncertain environments, highlighting recent advances and future challenges.

Contribution

It provides a comprehensive categorization and systematic review of causal reinforcement learning approaches, outlining key concepts, methodologies, and open issues.

Findings

Causality enhances transferability and robustness of RL agents.

Systematic categorization of causal RL methods based on problems and techniques.

Identification of open challenges and future research directions in causal RL.

Abstract

Reinforcement learning is an essential paradigm for solving sequential decision problems under uncertainty. Despite many remarkable achievements in recent decades, applying reinforcement learning methods in the real world remains challenging. One of the main obstacles is that reinforcement learning agents lack a fundamental understanding of the world and must therefore learn from scratch through numerous trial-and-error interactions. They may also face challenges in providing explanations for their decisions and generalizing the acquired knowledge. Causality, however, offers a notable advantage as it can formalize knowledge in a systematic manner and leverage invariance for effective knowledge transfer. This has led to the emergence of causal reinforcement learning, a subfield of reinforcement learning that seeks to enhance existing algorithms by incorporating causal relationships into the learning process. In this survey, we comprehensively review the literature on causal reinforcement learning. We first introduce the basic concepts of causality and reinforcement learning, and then explain how causality can address core challenges in non-causal reinforcement learning. We categorize and systematically review existing causal reinforcement learning approaches based on their target problems and methodologies. Finally, we outline open issues and future directions in this emerging field.