Optimistic PAC Reinforcement Learning: the Instance-Dependent View

被引：0
|
作者：
Tirinzoni, Andrea [1 ]
Al-Marjani, Aymen [2 ]
Kaufmann, Emilie [3 ]
机构：
[1] Meta AI, United States
[2] UMPA, ENS Lyon, France
[3] Univ. Lille, CNRS, Inria, Centrale Lille, UMR 9189 - CRIStAL, France
来源：
Proceedings of Machine Learning Research | 2023年 / 201卷
关键词：
Compendex;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Markov processes
引用
收藏
页码：1460 / 1480
相关论文
共 50 条
  • [1] Optimistic PAC Reinforcement Learning: the Instance-Dependent View
    Tirinzoni, Andrea
    Al-Marjani, Aymen
    Kaufmann, Emilie
    INTERNATIONAL CONFERENCE ON ALGORITHMIC LEARNING THEORY, VOL 201, 2023, 201 : 1460 - 1480
  • [2] Beyond No Regret: Instance-Dependent PAC Reinforcement Learning
    Wagenmaker, Andrew
    Simchowitz, Max
    Jamieson, Kevin
    CONFERENCE ON LEARNING THEORY, VOL 178, 2022, 178 : 358 - 418
  • [3] On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
    Nguyen-Tang, Thanh
    Yin, Ming
    Gupta, Sunil
    Venkatesh, Svetha
    Arora, Raman
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 8, 2023, : 9310 - 9318
  • [4] Instance-Dependent l∞-Bounds for Policy Evaluation in Tabular Reinforcement Learning
    Pananjady, Ashwin
    Wainwright, Martin J.
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2021, 67 (01) : 566 - 585
  • [5] Instance-Dependent Partial Label Learning
    Xu, Ning
    Qiao, Congyu
    Geng, Xin
    Zhang, Min-Ling
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [6] PAC-Bayes bounds for stable algorithms with instance-dependent priors
    Rivasplata, Omar
    Parrado-Hernandez, Emilio
    Shawe-Taylor, John
    Sun, Shiliang
    Szepesvari, Csaba
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [7] Instance-Dependent Inaccurate Label Distribution Learning
    Kou, Zhiqiang
    Wang, Jing
    Jia, Yuheng
    Liu, Biao
    Geng, Xin
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2025, 36 (01) : 1425 - 1437
  • [8] An instance-dependent simulation framework for learning with label noise
    Keren Gu
    Xander Masotto
    Vandana Bachani
    Balaji Lakshminarayanan
    Jack Nikodem
    Dong Yin
    Machine Learning, 2023, 112 : 1871 - 1896
  • [9] Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation
    Huang, Jiayi
    Zhong, Han
    Wang, Liwei
    Yang, Lin F.
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
  • [10] An instance-dependent simulation framework for learning with label noise
    Gu, Keren
    Masotto, Xander
    Bachani, Vandana
    Lakshminarayanan, Balaji
    Nikodem, Jack
    Yin, Dong
    MACHINE LEARNING, 2023, 112 (06) : 1871 - 1896
12345