Exponential Hardness of Reinforcement Learning with Linear Function Approximation

被引：0
作者：
Kane, Daniel [1 ]
Liu, Sihan [1 ]
Lovett, Shachar [1 ]
Mahajan, Gaurav [2 ]
Szepesvári, Csaba [3 ,4 ]
Weisz, Gellért [5 ]
机构：
[1] University of California, San Diego, United States
[2] Yale University, United States
[3] DeepMind, London, United Kingdom
[4] University of Alberta, Edmonton, Canada
[5] University College London, London, United Kingdom
来源：
Proceedings of Machine Learning Research | 2023年 / 195卷
关键词：
Compendex;
D O I：
36th Annual Conference on Learning Theory, COLT 2023
中图分类号：
学科分类号：
摘要：
Reinforcement learning
引用
收藏
页码：1588 / 1617
相关论文
共 50 条
  • [21] An expansion for the sum of a product of an exponential and a Bessel function. II
    Paris, Richard B.
    arXiv, 2022,
  • [22] Adaptive evolution strategy with ensemble of mutations for Reinforcement Learning
    Ajani, Oladayo S.
    Mallipeddi, Rammohan
    Knowledge-Based Systems, 2022, 245
  • [23] Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey
    Ganai, Milan
    Gao, Sicun
    Herbert, Sylvia L.
    IEEE Open Journal of Control Systems, 2024, 3 : 310 - 324
  • [24] Finite mixture estimation algorithm for arbitrary function approximation
    University of Ljubljana, Faculty of Mechanical Engineering, Aškerceva 6, 1000 Ljubljana, Slovenia
    Stroj Vest, 2 (115-124):
  • [25] Approximation of the Probability Function of Adjacent Pulse Disturbances.
    Larsen, Guenter
    AEU. Archiv fur Elektronik und Ubertragungstechnik, 1979, 33 (10): : 403 - 406
  • [26] ON APPROXIMATION OF THE TRANSFER FUNCTION FOR A PULSE SHAPING CIRCUIT.
    Filanovsky, I.M.
    Stromsmoe, K.A.
    Journal Water Pollution Control Federation, 1980, : 592 - 596
  • [27] Special Issue on Aerospace and Mechanical Applications of Reinforcement Learning and Adaptive Learning Based Control
    How, Jonathan P.
    Chowdhary, Girish
    Walsh, Thomas
    JOURNAL OF AEROSPACE INFORMATION SYSTEMS, 2014, 11 (09): : 541 - 541
  • [28] ADAPTIVE LINEAR FUNCTION ELIMINATION FILTER
    PLOTKIN, E
    WULICH, D
    INTERNATIONAL JOURNAL OF ELECTRONICS, 1979, 47 (04) : 355 - 364
  • [29] Reinforcement Learning Based Techniques for Radar Anti-Jamming
    Institute of Space Technology, Electrical Engineering Department, Islamabad, Pakistan
    Proc. Int. Bhurban Conf. Appl. Sci. Technol., IBCAST, (1021-1025):
  • [30] Optimistic PAC Reinforcement Learning: the Instance-Dependent View
    Tirinzoni, Andrea
    Al-Marjani, Aymen
    Kaufmann, Emilie
    Proceedings of Machine Learning Research, 2023, 201 : 1460 - 1480
12345