Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agents

• URL: http://arxiv.org/abs/2608.17524v1
• Date: Tue, 18 Aug 2026 08:46:26 GMT
• Title: Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agents
• Abstract summary: This paper outlines a benchmark for Explainable Reinforcement Learning (XRL) methods.<n>We suggest evaluating XRL methods by how effectively their generated explanations help to diagnose and fix malfunctioning reinforcement learning (RL) agents.
• Score: 8.58480571859241
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This preliminary paper outlines a planned evaluation benchmark for Explainable Reinforcement Learning (XRL) methods. Current evaluations rely on functionally-grounded metrics like faithfulness and compactness, and on human-grounded proxies like subjective ratings or prediction accuracy. We suggest evaluating XRL methods by how effectively their generated explanations help to diagnose and fix malfunctioning reinforcement learning (RL) agents. We propose EvalXRL, a benchmark in which a Large Language Model (LLM) coding agent uses different XRL methods to diagnose a held-out malfunction in an RL agent, and then repair it. Our proposed benchmark iterates across (environment $\times$ malfunction $\times$ XRL method) tuples and uses the reward signal of the RL agents to form a final score for each XRL method. The coding agent may use the method interactively: invoke the XRL method, process its output, form new hypotheses on what is broken, and invoke the method again with parameters adjusted for testing these hypotheses. This closed-loop structure may be described as a simplified version of the scientific method. Some XRL methods provide self-evaluations that follow this pattern; we propose the first head-to-head comparison of multiple XRL methods in closed-loop usage.

Related papers

• Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL [55.05743310621117]
  Co-RL is a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from their peers.<n>We show that increasing cohort diversity, through heterogeneous model families, sizes, and rephrased training samples, reduces the correlated errors that drive self-reinforcing feedback loops.
  arXiv  Detail & Related papers  (2026-08-18T01:16:02Z)
• Sanity Checking Causal Representation Learning on a Simple Real-World System [11.429106388558925]
  We evaluate methods for causal representation learning on a simple, real-world system where these methods are expected to work.<n>We select methods representative of different approaches to CRL and find that they all fail to recover the underlying causal factors.<n>Our efforts highlight the contrast between the theoretical promise of the state of the art and the challenges in its application.
  arXiv  Detail & Related papers  (2025-02-27T13:56:54Z)
• XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques [36.28161138606551]
  Reinforcement Learning (RL) has demonstrated substantial potential across diverse fields, yet understanding its decision-making process is an ongoing challenge. This paper delves in to Explainable RL (XRL), a subfield of Explainable AI (XAI) aimed at unravelling the complexities of RL models. Our focus rests on state-explaining techniques, a crucial subset within XRL methods, as they reveal the underlying factors influencing an agent's actions at any given time.
  arXiv  Detail & Related papers  (2024-02-20T03:20:37Z)
• RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$ [12.111848705677142]
  We propose RL$3$, a hybrid approach that incorporates action-values, learned per task via traditional RL, in the inputs to Meta-RL.<n>We show that RL$3$ earns a greater cumulative reward in the long term compared to RL$2$ while drastically reducing meta-training time and generalizes better to out-of-distribution tasks.
  arXiv  Detail & Related papers  (2023-06-28T04:16:16Z)
• PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation [66.79238445033795]
  We propose a more strict SRL evaluation metric PriMeSRL. We show that PriMeSRL drops the quality evaluation of all SoTA SRL models significantly. We also show that PriMeSRLsuccessfully penalizes actual failures in SoTA SRL models.
  arXiv  Detail & Related papers  (2022-10-12T17:04:28Z)
• LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning [78.2286146954051]
  LCRL implements model-free Reinforcement Learning (RL) algorithms over unknown Decision Processes (MDPs) We present case studies to demonstrate the applicability, ease of use, scalability, and performance of LCRL.
  arXiv  Detail & Related papers  (2022-09-21T13:21:00Z)
• Contrastive Learning as Goal-Conditioned Reinforcement Learning [147.28638631734486]
  In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion is unstable. We show (contrastive) representation learning methods can be cast as RL algorithms in their own right.
  arXiv  Detail & Related papers  (2022-06-15T14:34:15Z)
• Learning to Prune Deep Neural Networks via Reinforcement Learning [64.85939668308966]
  PuRL is a deep reinforcement learning based algorithm for pruning neural networks. It achieves sparsity and accuracy comparable to current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-09T13:06:07Z)
• MushroomRL: Simplifying Reinforcement Learning Research [60.70556446270147]
  MushroomRL is an open-source Python library developed to simplify the process of implementing and running Reinforcement Learning (RL) experiments. Compared to other available libraries, MushroomRL has been created with the purpose of providing a comprehensive and flexible framework to minimize the effort in implementing and testing novel RL methodologies.
  arXiv  Detail & Related papers  (2020-01-04T17:23:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.