Model-free Posterior Sampling via Learning Rate Randomization
机构 * CMAP, École Polytechnique(École Polytechnique 的 CMAP) ; HSE University(俄罗斯高等经济大学) ; Duisburg-Essen University(杜伊斯堡- Essen 大学) ; Google DeepMind(谷歌DeepMind) ; Mohamed Bin Zayed University of AI, UAE(阿联酋人工智能大学) ; IDEMIA ; ENS Lyon(里昂高等师范学院)
专题命中 记忆与上下文管理 :planning(abstract);分类 cs.LG
Comments This revision fixed an error connected to an incorrect use of Proposition 7 inside of Lemma 4, and a misprint in Lemma 12. In the current version, we modified the martingale construction and applied the same argument as before; no results need to be modified as a result of these fixes
Journal ref Advances in Neural Information Processing Systems 36 (NeurIPS 2023)