The paper presents a convergence framework for deep $V$‑learning over a finite horizon $H$, deriving explicit bounds on policy loss by decomposing the Bellman update error into six residuals. It shows how $L^s$ concentrability controls expected $L^1$ loss, quantifies the impact of shared sampling across horizon levels, and provides optimal and near‑optimal sample allocations for statistical error rates. The work also establishes sharp action‑gap bounds under a margin condition, transfers optimal‑gap results to frozen‑iterate gaps, and offers consistency guarantees for generative‑reset approximate‑ERM procedures with exact action scores.
By Yury Kolomeytsev
arXiv:2602. 00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time.
By Jiamin Xu, Kyra Gan
arXiv:2606. 16515v1 Announce Type: cross Abstract: Hamilton-Jacobi-Bellman theory implies that the optimal goal-conditioned action depends on the goal only through the gradient of the goal-reaching distance at the current state, yet standard online GCRL still conditions the actor on the raw goal -- a signal that is geometrically uninformative when the goal is far from the data distribution.
By Swaminathan S K, Damiya Gondha, Theyanesh Eswaramoorthy Rajahkrishnan, Aritra Hazra
arXiv:2512.23927v3 Announce Type: replace-cross
Abstract: Fitted \(Q\)-iteration (FQI) is a standard regression-based method for optimal control in offline reinforcement learning, but its stability u...
By Lars van der Laan, Nathan Kallus
arXiv:2608.20909v1 Announce Type: new
Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...
By Xuyao Lin, Yixiang Shan, Jinru Duan, Tao Yang, Xinyu Zhao, Runyu Lei, Yiming Zhao, Jiaxin Fan, Zongbao Feng, Peng Jia
arXiv:2606. 09825v1 Announce Type: cross Abstract: Training reinforcement learning (RL) policies from scratch is costly: it requires careful reward and environment design, extensive tuning, and substantial computation.
By Anton Bolychev, Georgiy Malaniya, Sinan Ibrahim, Pavel Osinenko
arXiv:2608. 02034v1 Announce Type: new Abstract: Multi-step returns accelerate reward propagation in off-policy reinforcement learning, but couple the evaluation of each decision to the suboptimal logged actions that follow it, inducing a pessimistic bias that grows with the horizon.
By Abdelghani Ghanem, Mounir Ghogho
arXiv:2609.40149v1 Announce Type: new
Abstract: Policy regularization in offline reinforcement learning balances policy improvement against reliance on uncertain value estimates. This balance can dif...
By Seonvin Cho, Soohyun Choi, Songnam Hong
arXiv:2602. 12107v2 Announce Type: replace-cross Abstract: We study offline reinforcement learning under $Q^\star$-approximation and partial coverage, a setting that motivates practical algorithms such as Conservative $Q$-Learning (CQL; Kumar et al.
By Haolin Liu, Braham Snyder, Chen-Yu Wei
arXiv:2606. 29980v1 Announce Type: new Abstract: Zero-shot Transfer in Reinforcement Learning (RL) aims to train an agent that can generate optimal policies for any reward function, without additional learning at transfer time, while training only on reward-free trajectories.
By Louis Bagot (SyCoSMA), Mathieu Lefort (LIRIS, SyCoSMA, IRISA, MALT, UR), La\"etitia Matignon (SyCoSMA)
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
arXiv:2608. 03108v1 Announce Type: new Abstract: Offline reinforcement learning (offline RL) can benefit from nearby out-of-distribution (OOD) actions, but estimation errors at these actions may be amplified by bootstrapping.
By Yi Yang, Zhennan Chen, Mingfeng Lv, Hanlei Li, Zhengsen Ruan, Lvqing Yang