Causal Reinforcement Learning: A Survey

Published: 30 Nov 2023, Last Modified: 30 Nov 2023Accepted by TMLREveryoneRevisionsBibTeX
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 notable advantages by formalizing knowledge in a systematic manner and harnessing 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 provide a comprehensive review of the literature in this domain. We begin by introducing basic concepts in causality and reinforcement learning, and then explain how causality can help address key challenges faced by traditional reinforcement learning. We categorize and systematically evaluate existing causal reinforcement learning approaches, with a focus on their ability to enhance sample efficiency, advance generalizability, facilitate knowledge transfer, mitigate spurious correlations, and promote explainability, fairness, and safety. Lastly, we outline the limitations of current research and shed light on future directions in this rapidly evolving field.
Certifications: Survey Certification
Submission Length: Long submission (more than 12 pages of main content)
Previous TMLR Submission Url:
Assigned Action Editor: ~Bo_Dai1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 1338