arXiv:2602. 10430v2 Announce Type: replace-cross Abstract: Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures.
arXiv:2606. 03382v1 Announce Type: cross Abstract: While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments.
While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments. The failure does not stem from insufficient model capacity or overly restrictive clipping.
arXiv:2607. 22186v2 Announce Type: replace Abstract: Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data can destabilize optimization and ultimately cause policy collapse.
arXiv:2605. 25582v2 Announce Type: replace Abstract: Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces distribution mismatch that existing trust-region techniques mitigate primarily by enforcing conservative optimization, often leaving rich training signals underutilized.
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.
The paper introduces Persistent Negative Adversarial Distillation, a method that improves black-box on-policy distillation by maintaining a live pool of historical teacher–student comparisons to stabilize the discriminator’s negative distribution. By anchoring the discriminator with these persistent negatives, the approach reduces reward-estimation error and yields smoother, higher-performing student policies across multiple benchmarks. The study demonstrates that the choice of negative samples is a critical design factor in effective black-box distillation.
arXiv:2607. 08925v1 Announce Type: new Abstract: Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do.
arXiv:2606. 05888v1 Announce Type: new Abstract: Retry-based objectives such as pass@K and max@K optimize the best return obtained from multiple sampled trajectories, and recent work has shown that they can promote exploration without explicit exploration bonuses.
arXiv:2606. 19236v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from policy entropy collapse during training.
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:2605. 11020v2 Announce Type: replace-cross Abstract: Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories.
The paper investigates why Group Relative Policy Optimization (GRPO) benefits from per‑prompt normalization by examining the local curvature of the sequence‑level policy gradient. It shows that standard deviation normalization acts as an adaptive gradient, yielding a provably faster convergence rate than unnormalized REINFORCE under mild conditions, with the improvement tied to the average within‑prompt reward standard deviation. The authors also propose IS‑GRPO, an importance‑sampling variant that maintains alignment with the full gradient and offers a tighter convergence guarantee, and empirically validate these theoretical insights on GSM8K and MATH datasets at 1.5B and 7B model scales.