arxiv
PublishedNovember 5, 2026 at 5:00 AM
Near-Minimax Sample Complexity for Multi-Objective Reinforcement Learning under Generative Models
Publisher summary· verbatim
arXiv:2611.05562v1 Announce Type: cross Abstract: In multi-objective reinforcement learning, preferences may be specified only after data collection, requiring one dataset to support a continuum of reward trade-offs. We study finite discounted Markov decision processes with unknown transitions, $S$
Stay posted· Newsletter
Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.
Your email is used only to send The Bubble Brief. Privacy policy
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSkillEarth: Teaching General-Purpose Agents to Act on Earth via Skill Evolution14marxivZero-Shot Weight-Space Programming for Prediction and Classification of Target Variables in Structured Datasets14marxivInformation Limits of Replay-Free Recurrent State Migration14marxivRegularizing Treatment Leakage for LLM-based Uplift Estimation14mThe Bubble Brief
MON · WED · FRIRead AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.
Your email is used only to send The Bubble Brief. Privacy policy
Originally published on arxiv ↗