Metraipolis › archive › dc_756ff78538bd
Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning — arXiv:2608.14963
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14963
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:55:09.730Z
- SHA-256 of the archived text
7d75c878a0a39eb7751463f984d7332907bcc504adc916264f828d203783f646- Stable URL of this page
https://metraipolis.com/documento/dc_756ff78538bd
How to cite
Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning — arXiv:2608.14963 — arXiv (en), https://arxiv.org/abs/2608.14963 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_756ff78538bd (Metraipolis archive dc_756ff78538bd, sha256 7d75c878a0a39eb7751463f984d7332907bcc504adc916264f828d203783f646)
BibTeX
@misc{dc756ff78538bd,
title = {Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning — arXiv:2608.14963},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14963},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_756ff78538bd; sha256 7d75c878a0a39eb7751463f984d7332907bcc504adc916264f828d203783f646},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14963. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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." Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2608.14963 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:13.970Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).