mlsanityData to 14 Oct 2026

A Comparative User Evaluation of XRL Explanations using Goal Identification

arXiv 2510.16956 ↗First posted 19 Oct 2025cs.AIcited by 1

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

Debugging is a core application of explainable reinforcement learning (XRL) algorithms; however, limited comparative evaluations have been conducted to understand their relative performance. We propose a novel evaluation methodology to test whether users can identify an agent's goal from an explanation of its decision-making. Utilising the Atari's Ms. Pacman environment and four XRL algorithms, we find that only one achieved greater than random accuracy for the tested goals and that users were generally overconfident in their selections. Further, we find that users' self-reported ease of identification and understanding for every explanation did not correlate with their accuracy.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 11 of its 19 references that are in the map. First posted on arXiv 19 Oct 2025.

Builds on

11 of 19 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Objective Metrics for Human-Subjects Evaluation in Explainable Reinforcement Learning31 Jan

Other references · 10

  1. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  2. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  3. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  4. 2020Explainable Reinforcement Learning: A Surveycited by 141
  5. 2019Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attributioncited by 50
  6. 2018Transparency and Explanation in Deep Reinforcement Learning Neural Networkscited by 40
  7. 2023GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanationscited by 17
  8. 2022Integrating Policy Summaries with Reward Decomposition for Explaining Reinforcement Learning Agentscited by 10
  9. 2024Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PCcited by 7
  10. 2022Experiential Explanations for Reinforcement Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques
  2. 2025A Survey of Explainable Reinforcement Learning: Targets, Methods and Needs
  3. 2026Textual Explanations and Their Evaluations for Reinforcement Learning Policy
  4. 2022Decisions that Explain Themselves: A User-Centric Deep Reinforcement Learning Explanation System
  5. 2026BXRL: Behavior-Explainable Reinforcement Learning
  6. 2025Interactive Explanations for Reinforcement-Learning Agents
  7. 2026Explaining Reinforcement Learning Agents via Inductive Logic Programming
  8. 2024Abstracted Trajectory Visualization for Explainability in Reinforcement Learning