A Survey on Explainable Deep Reinforcement Learning
This is an incremental survey that addresses the need for interpretability in DRL to improve trust and deployment in high-stakes applications.
The paper tackles the problem of interpretability in Deep Reinforcement Learning (DRL) by surveying Explainable Deep Reinforcement Learning (XRL) methods, which enhance transparency through various explanation techniques, and it reviews their applications in policy refinement, adversarial robustness, and integration with Large Language Models.
Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making tasks across diverse domains, yet its reliance on black-box neural architectures hinders interpretability, trust, and deployment in high-stakes applications. Explainable Deep Reinforcement Learning (XRL) addresses these challenges by enhancing transparency through feature-level, state-level, dataset-level, and model-level explanation techniques. This survey provides a comprehensive review of XRL methods, evaluates their qualitative and quantitative assessment frameworks, and explores their role in policy refinement, adversarial robustness, and security. Additionally, we examine the integration of reinforcement learning with Large Language Models (LLMs), particularly through Reinforcement Learning from Human Feedback (RLHF), which optimizes AI alignment with human preferences. We conclude by highlighting open research challenges and future directions to advance the development of interpretable, reliable, and accountable DRL systems.