Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning

[2608.14963] Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14963 (cs) [Submitted on 15 Aug 2026] Title: Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning Authors: Joanikij Chulev , Hendrik Baier View a PDF of the paper titled Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning, by Joanikij Chulev and 1 other authors View PDF HTML (experimental) Abstract: Pareto Conditioned Networks learn multiple multi-objective reinforcement learning behaviours by conditioning a single policy on a desired return command. However, the local mapping from command and state to action remains opaque. We propose command-space counterfactual explanations for PCNs: given a fixed state, original command, and foil action, we search, in a black-box setting, for a minimally changed desired-return command under which the same trained policy would choose the foil. Our contributions are threefold. First, we formulate PCN explanations as return-command interventions, using a return-only PCN variant that avoids the added ambiguity of horizon-conditioning. Second, we adapt adversarial machine learning methods to reinforcement-learning explanations. Third, we introduce a boundary-seeded directional search that improves over purely local optimization in the command-action landscape, resulting in our proposed approach CF-ZOO. The resulting explanations are actionable and intuitively expressed in the user's own preferences: "If your trade-off had shifted slightly towards X, the agent would have chosen Y." Comments: 11 pages, 3 figures Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) Cite as: arXiv:2608.14963 [cs.LG] (or arXiv:2608.14963v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14963 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Proceedings of the IJCAI-ECAI 2026 Workshop on Explainable Artificial Intelligence (XAI), Bremen, Germany, August 2026 Submission history From: Joanikij Chulev [ view email ] [v1] Sat, 15 Aug 2026 01:32:28 UTC (412 KB) Full-text links: Access Paper: View a PDF of the paper titled Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning, by Joanikij Chulev and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI cs.HC References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning#612401
• AVCG: A Generalized Variational Framework for Counterfactual Generation under Hypothesis Distributions#985327
• Biased processing of multiple outcomes in human reinforcement learning: evidence from computational modeling and eye-tracking#403419
• Biased processing of multiple outcomes in human reinforcement learning: evidence from computational modeling and eye-tracking#16223
• Grounding Actual Responsibility in Counterfactual Actions#112749