paper-with-me

홈 › Papers

A Comparative User Evaluation of XRL Explanations using Goal Identification

2025-10-19 · Mark Towers, Yali Du, Christopher Freeman, Timothy J. Norman 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.

📄 PDF Abstract BibTeX arXiv:2510.16956

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Comparative Explanations of Recommendations

2021-11-01 · Aobo Yang, Nan Wang, Renqin Cai, Hongbo Deng 외

As recommendation is essentially a comparative (or ranking) process, a good explanation should illustrate to users why an item is believed to be better than another, i.e., comparative explanations about the recommended i…

Explainable RecommendationRecommendation SystemsSentence

Can Offline Metrics Measure Explanation Goals? A Comparative Survey Analysis of Offline Explanation Metrics in Recommender Systems

2023-10-22 · André Levi Zanon, Marcelo Garcia Manzato, Leonardo Rocha

Explanations in a Recommender System (RS) provide reasons for recommendations to users and can enhance transparency, persuasiveness, engagement, and trust-known as explanation goals. Evaluating the effectiveness of expla…

DiversityPersuasivenessRecommendation SystemsSentence

Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News

2021-04-27 · NAACL (NLP4IF) 2021 6 · Ashkan Kazemi, Zehua Li, Verónica Pérez-Rosas, Rada Mihalcea

In this paper, we explore the construction of natural language explanations for news claims, with the goal of assisting fact-checking and news evaluation applications. We experiment with two methods: (1) an extractive me…

Fact CheckingLanguage ModelingLanguage ModellingMisinformation

Explainability for Machine Learning Models: From Data Adaptability to User Perception

2024-02-16 · Julien Delaunay

This thesis explores the generation of local explanations for already deployed machine learning models, aiming to identify optimal conditions for producing meaningful explanations considering both data and user requireme…

counterfactualCounterfactual ExplanationExplanation Generation

Explainable Recommendation with Comparative Constraints on Product Aspects

2021-03-08 · International Conference on Web Search and Data Mining 2021 3 · Trung-Hoang Le, Hady W. Lauw

To aid users in choice-making, explainable recommendation models seek to provide not only accurate recommendations but also accompanying explanations that help to make sense of those recommendations. Most of the previous…

Explainable Recommendation