Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction. This offline-to-online RL (O2O-RL) paradigm is particularly promising in nonstationary domains where interaction is costly or potentially hazardous.
arXiv:2607. 13389v1 Announce Type: new Abstract: Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget.
arXiv:2607. 11720v1 Announce Type: cross Abstract: Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction.
MInTRL (Minimal Intervention Reinforcement Learning) expands exploration in on-policy reinforcement learning by inserting sparse, local corrections into rollouts via a judge-intervention policy. These interventions replace erroneous suffixes and immediately return control to the main policy, allowing the agent to explore beyond its natural trajectory while maintaining on-policy data. The method uses a sequence-level advantage-regression objective, avoiding importance sampling, and demonstrates superior performance on math and code benchmarks compared to standard on-policy and off-policy baselines.
The paper proposes a method for allocating limited counterfactual annotation resources from multiple sources—such as domain experts and large language models—to improve off-policy evaluation in contextual bandits. By formulating an integer optimization problem that balances source-specific costs and error rates, the authors derive a majorization‑minimization algorithm that iteratively reduces estimator variance. Experiments on synthetic clinical and education bandit data demonstrate that the optimized allocation cuts mean‑squared error by over 20% compared to no annotation.
The paper introduces Task Specialization Fine-Tuning (TSFT), an online framework that allocates a limited fine‑tuning budget across multiple task regions in Contextual Reinforcement Learning. TSFT predicts fine‑tuning performance with a simple parametric model and solves the budget allocation problem exactly using integer linear programming. Experiments on combinatorial optimization, continuous control, and LLM fine‑tuning show that TSFT outperforms baselines in task coverage and approaches oracle performance.
arXiv:2508. 10123v3 Announce Type: replace-cross Abstract: Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT).
arXiv:2503. 00539v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs).
arXiv:2608. 19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models.
Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy advantages from multiple rollouts, avoiding the substantial memory overhead of conventional proximal policy optimization (PPO) and achieving strong performance on long-horizon interactive tasks.
Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift from a reference policy. A standard way to balance this trade-off is via a KL-regularized RL objective, although this formulation does not by itself provide a principled way to set the regularization coefficient.
The paper presents a new scaling law for reward optimization in AI alignment, showing that performance scales as Θ(√min{log(M), K}), where M is the number of preference comparisons used to train a proxy reward model and K is the KL‑divergence budget relative to a reference policy. The authors derive this law using an information‑theoretic model, prove its tightness, and validate it with extensive experiments involving a 70B gold reward model and smaller proxy models (0.6B–4B). The empirical results demonstrate a strong fit (R² 97–99 %) across different model sizes, noise levels, and optimization methods, suggesting that reward optimization behaves like a simple selection task over IID Gaussian variables with noisy feedback.