arXiv:2506. 00818v2 Announce Type: replace-cross Abstract: Offline reinforcement learning for longitudinal studies often faces two linked challenges: rewards may be binary or bounded, and reward observations may be available only for a subset of trajectories or time points even when the corresponding state-action-next-state histories are available.
By Sinian Zhang, Kaicheng Zhang, Ziping Xu, Zongqi Xia, Jue Hou, Tianxi Cai, Doudou Zhou
arXiv:2607. 14346v1 Announce Type: new Abstract: Policy learning methods are increasingly used to inform treatment allocation under budget constraints.
By Johnna Sundberg, Rayid Ghani, Eli Ben-Michael, Edward Kennedy
arXiv:2602. 03778v2 Announce Type: replace-cross Abstract: Tail-end risk measures such as static conditional value-at-risk (CVaR) are used in safety-critical applications to prevent rare, yet catastrophic events.
By Aneri Muni, Vincent Taboga, Esther Derman, Pierre-Luc Bacon, Erick Delage
arXiv:2606. 26080v1 Announce Type: new Abstract: Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreversible actions, and stochastic environment feedback make both human annotation and Monte Carlo estimation infeasible at scale.
By Changdae Oh, Wendi Li, Seongheon Park, Samuel Yeh, Tanwi Mallick, Sharon Li
arXiv:2607. 28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.
By Brett Daley
arXiv:2606. 18531v1 Announce Type: cross Abstract: Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets record only trajectory-level outcomes.
By Xuanfei Ren, Tengyang Xie