arXiv:2505. 23878v2 Announce Type: replace-cross Abstract: Optimizing pretraining data composition is pivotal for LLM generalization.
arXiv:2607. 19399v1 Announce Type: cross Abstract: It is commonly observed that online reinforcement learning (RL) produces better-performing strategies than offline methods across a broad range of performance measures.
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.
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...
arXiv:2606. 24133v1 Announce Type: new Abstract: The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language Model (LLM) pre-training.
arXiv:2608. 10473v1 Announce Type: cross Abstract: Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction.
The paper investigates how reusing past samples can improve the sample efficiency of Proximal Policy Optimization (PPO). Two variants, wPPO-U and wPPO-BH, are introduced within a multiple importance weighting framework, each reusing data from recent iterations while preserving core PPO mechanics. The authors derive theoretical policy improvement bounds for both variants and empirically evaluate their impact on continuous control tasks.
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:2606. 15333v1 Announce Type: cross Abstract: LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility.
arXiv:2608. 01205v1 Announce Type: new Abstract: Recent offline reinforcement learning methods increasingly rely on expressive generative policies and specialized value-guidance mechanisms.
arXiv:2502. 19544v3 Announce Type: replace Abstract: Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL).
The paper introduces LAC (Light Actor, deep Critic), an offline reinforcement learning approach that allocates model capacity to a deep critic rather than a complex actor to improve inference efficiency. It addresses three failure modes—optimization, bootstrap-noise amplification, and value-range drift—using a residual MLP backbone, n‑step bootstrap targets, and a categorical cross‑entropy loss. Experiments on OGBench show LAC matches state‑of‑the‑art diffusion and flow‑matching baselines while reducing inference latency by up to four times.
arXiv:2601. 11960v3 Announce Type: replace-cross Abstract: Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference responses.