Skip to content
Log in
Sponsored AI Networking Cookbook: Practical recipes for AI-assisted network automation and development AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Review

A survey on explainable reinforcement learning: state of the art, challenges and opportunities

Daniele Melloni Andrea Zingoni
Jul 2026 · Data mining and knowledge discovery · Vol 40 · 0 citations · 95 references
Computer Science

TL;DR

From this literature review, it becomes evident, in face of a series of preliminary and promising studies, the field of XRL still lacks a proper accounting towards full explainability and it emerges that more effort should be devolved into developing paradigms with a human-in-the-loop factor and standardized metrics should be adopted to allow a fair comparison of different explanation methods.

DOI Semantic Scholar
View source

Similar papers

Jul 2026

Explaining Reinforcement Learning Agents via Inductive Logic Programming

This work employs Inductive Logic Programming (ILP) to extract symbolic representations of RL policies and define a novel set of explainability metrics, including activation rate, feature coverage, syntactic distance and semantic distance, which provide crucial insights for the transfer and generalization of action-spe...

Celeste Veronese, Edoardo Zorzi, Daniele Meli et al. · 0 citations
Preprint Jul 2026

Explaining Reinforcement Learning Decisions in Self-adaptive Systems

Reinforcement Learning (RL) has been extensively used in autonomous and self-* systems, but RL policies, especially deep RL ones relying on neural networks, lack transparency and are difficult to understand. This can lead to diminished user trust, and makes for a more challenging verification of systems. To address thi...

Jasmina Gajcin, Juan C. Rosero, Ivana Dusparic · 0 citations
Review Open access 2020

Explainable Reinforcement Learning for Transparent Automation

This work reviews pre-2019 XRL approaches, categorizing them into policy explanation, reward decomposition, model transparency, and post-hoc interpretability methods, and proposes a framework that combines interpretable policies, surrogate models, attention mechanisms, and visualization techniques to enhance transparen...

Michael Anderson, David Thompson · 0 citations
Book Open access Aug 2026

Large Language Model (LLM) as an Excellent Reinforcement Learning Researcher in both Single-Agent and Multi-Agent Scenarios

A Self-Evolutional single-agent/multi-agent Reinforcement Learning (SE-RL) framework that utilizes a Large Language Model (LLM) to design various RL algorithm modules, such as agent model design, reward function, profiling, communication, and state imagination, by leveraging the LLM generating module output or code.

Vincent Fu, Xin-Xin Xu, Weichen Xu et al. · 0 citations
#machine learning Preprint Aug 2026

Demystifying Reinforcement Learning Post-Training of Language Models

This work deconstructs the RL post-training algorithm, investigating each step to clarify what is actually happening beneath the surface, and uses the entropy of the policy's output distribution as a lens to compare the distributions learned through pretraining, SFT, and RL post-training, revealing how each stage shape...

D. Clay, Saket Gollapudi, Sankar V Harilal et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.