arxiv
PublishedSeptember 1, 2026 at 4:00 AM
Continuity-Free Near-Minimax Leading-Order Regret for CVaR-UCBVI
Publisher summary· verbatim
arXiv:2608.28960v1 Announce Type: new Abstract: For finite-horizon tabular CVaR reinforcement learning, prior work proves a $\widetilde{O}(\tau^{-1}\sqrt{SAK})$ leading regret bound for arbitrary normalized return laws and the sharper $\widetilde{O}(\sqrt{SAK/\tau})$ rate under a density lower bound
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
arxivAn AI Security Agent for University ACMIS: Multi-Vector Threat Detection and Automated Response53marxivNavalia: Advancing Cowork Agents through Verifiable Task Synthesis and Long-Horizon Post-Training53marxivLarge language model and reinforcement learning based autonomous construction and progress updates53marxivPareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models53mThe 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 ↗