SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidanceby Liyu Zhang, Haochi Wu, Xu Wan,…
SkiLD: Unsupervised Skill Discovery Guided by Factor Interactionsby Zizhao Wang, Jiaheng Hu, Caleb Chuck, Stephen…
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Modelsby Michael Noukhovitch, Shengyi Huang,…
Leveraging Skills from Unlabeled Prior Data for Efficient Online Explorationby Max Wilcoxson, Qiyang Li, Kevin…
Prioritized Generative Replayby Renhao Wang, Kevin Frans, Pieter Abbeel, Sergey Levine, Alexei A. EfrosFirst submitted…
Scalable Offline Reinforcement Learning for Mean Field Gamesby Axel Brunnbauer, Julian Lemmel, Zahra Babaiee, Sophie…
Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularityby Philip Amortila, Dylan J. Foster,…
Learning Versatile Skills with Curriculum Maskingby Yao Tang, Zhihui Xie, Zichuan Lin, Deheng Ye, Shuai…
Primal-Dual Spectral Representation for Off-policy Evaluationby Yang Hu, Tianyi Chen, Na Li, Kai Wang, Bo…
Entity-based Reinforcement Learning for Autonomous Cyber Defenceby Isaac Symes Thompson, Alberto Caron, Chris Hicks, Vasilios…