PAC-Bayesian Reinforcement Learning Trains Generalizable Policies 文章

ArXiv CS.AI2026-06-01NEWSen作者: Abdelkrim Zitouni, Mehdi Hennequin, Juba Agoun, Ryan Horache, Nadia Kabachi, Omar Rivasplata
查看原文 →
关系图谱

PAC-Bayesian Reinforcement Learning Trains Generalizable Policies · 相关技术

相关技术

PB-SACSoft Actor-Criticmixing timePAC-Bayesian generalization bound