arXiv:2607. 26680v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown remarkable success across a wide range of complex tasks.
By Mingxuan Che, Tsung-Yuan Tseng, Theresa Eimer, Marius Lindauer, Alexander von Rohr
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.
By Hua Zheng, Wei Xie, M. Ben Feng, Keilung Choy
arXiv:2505. 22442v3 Announce Type: replace-cross Abstract: Offline RL (ORL) promises safe and sample-efficient deployment but existing methods rely on undocumented online interactions for hyperparameter tuning and lack reliable fully offline estimates of initial online performance.
By Mattie Fellows, Clarisse Wibault, Uljad Berdica, Johannes Forkel, Maike Osborne, Jakob N. Foerster
arXiv:2606. 05606v1 Announce Type: new Abstract: LLM post-training often relies on reinforcement learning methods that sample multiple rollouts per prompt, yet most existing approaches use a fixed rollout budget for every prompt, despite large differences in the training signal different prompts provide.
By Yiming Zong, Yige Wang, Jiashuo Jiang
arXiv:2511. 02570v3 Announce Type: replace Abstract: Bayesian optimization (BO) is a widely used approach to hyperparameter optimization (HPO).
By Lukas Fehring, Marcel Wever, Maximilian Splieth\"over, Leona Hennig, Henning Wachsmuth, Marius Lindauer
arXiv:2511. 23310v3 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective paradigm for post-training large language models, yet the design of its baselines and learning-rate schedules remains largely heuristic.
By Zixun Huang, Jiayi Sheng, Zeyu Zheng