Explaining Reinforcement Learning Decisions in Self-adaptive Systems
On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL
Abstract (arXiv)
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 this challenge, this paper introduces Explanations using Alternative Realities for Reinforcement Learning (EARL), a Python library to produce counterfactual explanations in RL settings. This library allows the user to produce explanations by exploring What-if scenarios to clarify agent behavior by comparing possible outcomes. Counterfactual explanations have been shown to be intuitive and user-friendly in psychology research, but have only recently been explored in RL, with existing implementations usually limited to toy examples and benchmarks. EARL supports counterfactual explanation generation in realistic RL-based self-adaptive systems. To demonstrate its applicability, we demonstrate its use in a simulation of CitiBikes, a self-adaptive bike-sharing system, and we provide evaluations showing how it performs in real applications.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 31 references that are in the map. First posted on arXiv 13 Jul 2026.
Builds on
17 of 31 references.
References · 17
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
- 2017Visualizing and Understanding Atari Agentscited by 141
- 2019Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attributioncited by 50
- 2021Counterfactual Explanations for Machine Learning: Challenges Revisitedcited by 19
- 2023GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanationscited by 17
- 2019Counterfactual States for Atari Agents via Generative Deep Learningcited by 14
- 2022Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunitiescited by 13
- 2020Automatic Discovery of Interpretable Planning Strategiescited by 9
- 2023CoverNav: Cover Following Navigation Planning in Unstructured Outdoor Environment with Deep Reinforcement Learningcited by 7
- 2023RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learningcited by 6
5 more
- 2021Making Things Explainable vs Explaining: Requirements and Challenges under the GDPRcited by 4
- 2022ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learningcited by 4
- 2021Enhancing Human-in-the-Loop Adaptive Systems through Digital Twins and VR Interfacescited by 3
- 2023A User Study on Explainable Online Reinforcement Learning for Adaptive Systemscited by 3
- 2024Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systemscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2022Decisions that Explain Themselves: A User-Centric Deep Reinforcement Learning Explanation System
- 2025Counterfactual Explanations for Continuous Action Reinforcement Learning
- 2025Explainable Reinforcement Learning Agents Using World Models
- 2024Explaining Reinforcement Learning: A Counterfactual Shapley Values Approach
- 2024Semifactual Explanations for Reinforcement Learning
- 2024ACTER: Diverse and Actionable Counterfactual Sequences for Explaining and Diagnosing RL Policies
- 2025A Survey of Explainable Reinforcement Learning: Targets, Methods and Needs
- 2021Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning