arXiv:2608. 07719v1 Announce Type: new Abstract: Offline reinforcement learning repeatedly trains policies from a fixed transition pool, making redundant data costly across seeds and hyperparameters, while naive subsampling can remove rare transitions needed for long-horizon credit assignment.
Headroom-Drift Replay is a replay control primitive designed for GRPO that separates reuse into two decisions: Headroom ranks stored groups by remaining learning value, while Drift gates them by compatibility with the current policy. The method keeps the fresh on‑policy stream unchanged and adds no auxiliary generation or training machinery. Across mathematical reasoning, multimodal reasoning, and Agentic Search benchmarks, it outperforms naive replay and matches or exceeds broader replay methods on Avg Mean@32, delivering comparable quality at materially lower wall‑clock time in Agentic Search.
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:2607. 22724v1 Announce Type: cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or steps within a group.
The paper investigates the problem of sharing a single critic across multiple parallel environments in reinforcement learning. It shows that when environments assign different expected returns to the same state, a shared critic must reconcile conflicting value targets, which can distort advantage estimates and misguide policy updates. The authors propose a simple fix—providing the critic with the environment index—demonstrating through bandit models and experiments on CartPole, MuJoCo, BipedalWalker, and 16 Procgen games that this conditional critic stabilizes learning and boosts returns, achieving a 40.8% improvement in aggregate normalized return on unseen levels.
arXiv:2608. 15088v1 Announce Type: cross Abstract: Human-in-the-loop (HIL) online reinforcement learning for real robots must absorb human interventions quickly while continuing to improve beyond the human prior.
arXiv:2602. 05379v2 Announce Type: replace-cross Abstract: Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data to improve sample efficiency and accelerate policy optimization.
arXiv:2610.20318v1 Announce Type: cross Abstract: Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload...
arXiv:2607. 04470v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-agent reinforcement learning (MARL), yet the training-time dynamics of this integration remain poorly understood.
arXiv:2607.27422v2 Announce Type: replace Abstract: Goal-conditioned action generators can produce many plausible actions. Best-of-\(K\) selection then uses a critic to rank those actions for the cur...
The paper investigates what information must be preserved in replay buffers for class‑incremental learning. By treating cached predictions as temporally heterogeneous supervision, the authors separate classes known at storage time from those learned later, and evaluate the impact of deleting logit matching. Experiments on CIFAR‑100 with DER++ show that a simple task‑level offset can largely correct the cost of removing later‑class matching, while the cost of disrupting class correspondence remains.
The paper introduces Cross-Behavior Policy Optimization (CBPO), a method that unifies offline demonstrations and policy-generated rollouts into a single regression loss using a fixed-reference target. CBPO eliminates the need for separate supervised fine‑tuning and reinforcement learning objectives, allowing positive and negative offline completions, reference responses, and current and historical rollouts to share a common reward‑labeled format and replay buffer. Experiments on two model scales and four mathematical reasoning benchmarks show that CBPO, especially the CBPO‑Unified variant, outperforms baseline methods in avg@32 and pass@32 metrics, with historical rollouts providing additional gains.