Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 00164v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards can in principle train calibrated probabilistic forecasters, since a proper scoring rule such as the Brier score is computed from outcomes alone and is minimized in expectation by the true probability.
arXiv:2605. 11752v2 Announce Type: replace Abstract: Federated learning relies on effective client selection to alleviate the performance degradation caused by data heterogeneity.
arXiv:2607. 00531v1 Announce Type: cross Abstract: Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open challenge.
arXiv:2607. 00392v1 Announce Type: cross Abstract: Unsupervised Reinforcement Learning (URL) aims to pre-train scalable, skill-conditioned policies without extrinsic rewards, serving as a foundation for downstream control tasks.
arXiv:2607. 01083v1 Announce Type: cross Abstract: High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates.
arXiv:2607. 01225v1 Announce Type: cross Abstract: Prior work on imitation learning from suboptimal demonstrations typically relies on compressed supervision signals such as confidence estimates, discriminator scores, or importance weights.
arXiv:2601. 14232v2 Announce Type: replace-cross Abstract: Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle multiple sources of shift and hinder systematic analysis.
arXiv:2607. 00796v1 Announce Type: new Abstract: Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks.
arXiv:2607. 01170v1 Announce Type: cross Abstract: Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they are slow at inference: an autoregressive (AR) decoder spends one sequential forward pass per reasoning token, and the reasoning trace far exceeds the ranking it produces.
arXiv:2607. 00926v1 Announce Type: cross Abstract: Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data from the target domain is entirely or partially unavailable.
arXiv:2607. 00056v1 Announce Type: cross Abstract: This paper studies energy efficient tracking of power-limited mobile users with the assistance of a Reconfigurable Intelligent Surface (RIS).
arXiv:2312. 15427v3 Announce Type: replace Abstract: Stochastic optimization is a widely used approach for optimization under uncertainty, where uncertain input parameters are modeled by random variables.
arXiv:2607. 00680v1 Announce Type: new Abstract: We study distributed online submodular maximization under partition matroid constraints, in which multiple agents select a limited number of actions from their own subsets sequentially to maximize the cumulative value of a sequence of objective functions.
arXiv:2509. 06810v3 Announce Type: replace-cross Abstract: Humans can uniquely assign value to novel, abstract outcomes to support reinforcement learning.
arXiv:2606. 25198v2 Announce Type: replace Abstract: Autonomous AI Research promises to accelerate the scientific progress of machine learning.
arXiv:2510. 04140v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a widely adopted technique for enhancing the reasoning ability of Large Language Models (LLMs).
arXiv:2607. 00811v1 Announce Type: new Abstract: Unsupervised pre-training on large-scale datasets has demonstrated significant potential for improving the sample efficiency and performance of Reinforcement Learning (RL).
arXiv:2607. 00442v1 Announce Type: cross Abstract: Reinforcement learning (RL) for quadruped locomotion commonly depends on fixed, hand-crafted, and Markovian reward functions that limit both interpretability of learned policies and lack explicit control over gait behaviors.
arXiv:2607. 00924v1 Announce Type: new Abstract: Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning.
arXiv:2607. 00407v1 Announce Type: new Abstract: Slide design requires personalizing both deck themes and page layouts.