Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions

[2608.14642] Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14642 (cs) [Submitted on 29 Jul 2026] Title: Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions Authors: Prabhjyot Singh , Majid Ghasemi , Mark Crowley View a PDF of the paper titled Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions, by Prabhjyot Singh and 2 other authors View PDF HTML (experimental) Abstract: Reinforcement Learning (RL) agents trained on a single reward signal exploit the gap between the designed reward and the intended behavior. This is particularly a problem when we are trying to imbue ethical behavior into RL agents. An agent can look ethical on average while concentrating its violations in a few bad episodes, and a creature in the environment harmed in one episode is not restored by good conduct in another. We compare four ways of training ethical behavior in Craftax, an open-ended survival benchmark. The four are: scalar penalties with termination, a linear multi-objective weight sweep, an adaptive Lagrangian constraint, and a non-compensatory utility optimized per episode under the Expected Scalarized Returns (ESR) criterion. All are evaluated under a single detector-based protocol that counts every violation in every episode without censoring. On the frontier of mean return against mean violation rate, the four methods are indistinguishable; per episode they separate sharply. At matched mean return, the ESR agent holds its stated budget of one violation in effectively every episode (worst-decile 1.04 +/- 0.07 violations), the Lagrangian leaks past the same budget (1.14 +/- 0.03), and the weight sweep's worst episodes double it (2.20 +/- 0.20). An observation-augmentation control attributes the separation to the training objective rather than to what the agent observes, and the per-episode guarantee costs nothing on the mean frontier. When ethical violations do not average away across episodes, we argue both training and evaluation must target the per-episode distribution rather than the mean. Comments: 11 Pages, Under Review Subjects: Machine Learning (cs.LG) Cite as: arXiv:2608.14642 [cs.LG] (or arXiv:2608.14642v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14642 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Prabhjyot Singh [ view email ] [v1] Wed, 29 Jul 2026 00:00:22 UTC (791 KB) Full-text links: Access Paper: View a PDF of the paper titled Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions, by Prabhjyot Singh and 2 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 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

• Can model-free reinforcement learning explain deontological moral judgments?#83583
• Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best#1069926
• Norms and Causation in Artificial Morality#118674
• Knowledge and Morality Without Certainty: A Bayesian Framework#73106
• The Methods of Ethics#52863