The paper introduces a framework for optimal policy improvement in reinforcement learning, defining it as the best single update under given constraints. It shows that restricting improvement to a subset of states is equivalent to solving an induced Markov Decision Process, linking planning with explicit or implicit models to optimal policy improvement. The authors develop a novel operator for greedification under approximate evaluation, demonstrating empirical gains across several RL algorithms and settings.
By Yaniv Oren, Viliam Vadocz, Wiktor Zabka, Thomas Evers, Jan Robine, Wendelin B\"ohmer, Matthijs T. J. Spaan, Martha White, Hendrik Baier, Fenghui Yu
arXiv:2607. 28390v1 Announce Type: new Abstract: Constrained Markov Decision Processes (CMDPs) provide a natural framework for reinforcement learning in safety-critical applications, where agents maximize long-term reward while satisfying long-term constraints.
By Ankur Naskar, Vaneet Aggarwal
The paper investigates continuous‑time stochastic control problems with unknown drift and running reward functions, using an exploratory reinforcement learning framework that incorporates relaxed controls and entropy regularization. It develops policy‑iteration algorithms based on probabilistic representations of the optimal value function and its gradient, proving convergence and demonstrating performance through numerical examples. The study also extends to a special case with control‑dependent diffusion, requiring a Hessian representation.
By Jin Ma, Gaozhan Wang, Jianfeng Zhang, Xunyu Zhou
arXiv:2606. 25012v1 Announce Type: new Abstract: Many reinforcement learning (RL) problems in the infinite-horizon average-reward setting require optimizing multiple conflicting objectives while satisfying multiple safety constraints.
By Ankur Naskar, Swetha Ganesh, Vaneet Aggarwal
arXiv:2607. 20152v1 Announce Type: cross Abstract: Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle.
By Nikola Milosevic, Nicol\'as Hinrichs, Nico Scherf
The paper introduces Multi-step Proximal Policy Improvement (MPI), a method that refines offline reinforcement learning policies through sequential re-centered proximal steps. By viewing policies as a probability manifold, MPI interprets a wide range of offline actor objectives as a single proximal policy improvement step and extends this to multiple steps for controlled policy improvement beyond the behavior distribution. Experiments on D4RL benchmarks demonstrate that a few MPI refinements enhance strong offline baselines such as TD3+BC, ReBRAC, and IQL, while diagnostics clarify the benefits of re-centered refinement over fixed-objective scheduling and highlight critic error limitations.
By Soohyun Choi, Seonvin Cho, Songnam Hong
arXiv:2605. 29032v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss.
By Christoph Dann, Yishay Mansour, Mehryar Mohri
arXiv:2608. 02951v1 Announce Type: cross Abstract: Preference-based reinforcement learning (PbRL) for general stochastic MDPs often requires training a reward model.
By Evan Assmus, Qining Zhang, Lei Ying
arXiv:2601. 22970v2 Announce Type: replace-cross Abstract: Policies learned via continuous actor-critic methods often exhibit erratic, high-frequency oscillations, making them unsuitable for physical deployment.
By Jeong Woon Lee, Kyoleen Kwak, Daeho Kim, Hyoseok Hwang
arXiv:2608. 11052v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations.
By Nikita Sevriukov, Anna Barabanova, Uliana Gagarina, Karina Ivanova, Sofiia Kasaeva, Ilya Levin, Marina Sheshukova
In value-based reinforcement learning, improving the accuracy of policy evaluation has been shown to improve downstream policy optimization performance. The widely adopted family of approximations rel...
Discounted exponential utility provides a principled criterion for risk-sensitive sequential decision-making, but its nonlinear structure complicates reinforcement learning. A recent work \citep{thoppe2026reinforcement} addressed this difficulty by introducing a Bellman-compatible surrogate and two model-free fixed-point algorithms for optimizing it over stationary policies.