Offline Policy Optimization with Posterior Sampling

arXiv:2605.19461v1 Announce Type: new Abstract: On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity,

arXiv:2610.02828v1 Announce Type: new Abstract: Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group

arXiv:2605.11151v1 Announce Type: new Abstract: Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online

arXiv:2605.01327v1 Announce Type: new Abstract: Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of

arXiv:2605.15603v1 Announce Type: cross Abstract: Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined

arXiv:2603.22292v1 Announce Type: cross Abstract: Sequential decision making using Markov Decision Process underpins many realworld applications. Both model-based and model free

arXiv:2606.14415v1 Announce Type: new Abstract: Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as

arXiv:2603.22829v1 Announce Type: new Abstract: With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted