Unifying Causal Reinforcement Learning: Survey, Taxonomy, Algorithms and Applications

📅 2025-12-19
📈 Citations: 0
Influential: 0
📄 PDF

career value

196K/year
🤖 AI Summary
Traditional reinforcement learning (RL) suffers from poor generalization, weak robustness, and limited interpretability under distributional shifts, confounding variables, and dynamic environments due to its reliance on correlational modeling. To address these limitations, this paper proposes a Causal Reinforcement Learning (CRL) framework that systematically integrates causal inference (CI) techniques. We introduce the first unified taxonomy covering five core directions: causal representation learning, counterfactual policy optimization, offline causal RL, causal policy transfer, and causal world modeling. We formally define three foundational paradigms—causal representation, counterfactual policy optimization, and causal transfer—and uncover a novel pathway for causal disentanglement under distributional shift. Leveraging structural causal models (SCMs), do-calculus, invariant risk minimization (IRM), and counterfactual policy evaluation, we comprehensively survey over 100 state-of-the-art works. Empirical results demonstrate that CRL significantly improves cross-environment generalization and decision trustworthiness in robotics control, healthcare decision-making, and recommender systems.

Technology Category

Application Category

📝 Abstract
Integrating causal inference (CI) with reinforcement learning (RL) has emerged as a powerful paradigm to address critical limitations in classical RL, including low explainability, lack of robustness and generalization failures. Traditional RL techniques, which typically rely on correlation-driven decision-making, struggle when faced with distribution shifts, confounding variables, and dynamic environments. Causal reinforcement learning (CRL), leveraging the foundational principles of causal inference, offers promising solutions to these challenges by explicitly modeling cause-and-effect relationships. In this survey, we systematically review recent advancements at the intersection of causal inference and RL. We categorize existing approaches into causal representation learning, counterfactual policy optimization, offline causal RL, causal transfer learning, and causal explainability. Through this structured analysis, we identify prevailing challenges, highlight empirical successes in practical applications, and discuss open problems. Finally, we provide future research directions, underscoring the potential of CRL for developing robust, generalizable, and interpretable artificial intelligence systems.
Problem

Research questions and friction points this paper is trying to address.

Integrates causal inference with reinforcement learning to address explainability and robustness issues
Categorizes approaches into causal representation, counterfactual optimization, and transfer learning
Aims to develop generalizable and interpretable AI systems through causal modeling
Innovation

Methods, ideas, or system contributions that make the work stand out.

Integrating causal inference with reinforcement learning
Modeling cause-and-effect relationships explicitly
Categorizing approaches into causal representation learning
🔎 Similar Papers
No similar papers found.
C
Cristiano da Costa Cunha
Department of Computer Science and Software Engineering, University of Western Australia, 6009 WA Australia
W
Wei Liu
Department of Computer Science and Software Engineering, University of Western Australia, 6009 WA Australia
T
Tim French
Department of Computer Science and Software Engineering, University of Western Australia, 6009 WA Australia
A
Ajmal Mian
Department of Computer Science and Software Engineering, University of Western Australia, 6009 WA Australia