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

页码：1588 / 1617

共 50 条

[21] Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency
Cai, Qi
Yang, Zhuoran
Wang, Zhaoran
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[22] Multiagent reinforcement learning using function approximation
Abul, O
Polat, F
Alhajj, R
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2000, 30 (04): : 485 - 497
[23] Resilient Multiagent Reinforcement Learning With Function Approximation
Ye, Lintao
Figura, Martin
Lin, Yixuan
Pal, Mainak
Das, Pranoy
Liu, Ji
Gupta, Vijay
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2024, 69 (12) : 8497 - 8512
[24] Ensemble Methods for Reinforcement Learning with Function Approximation
Fausser, Stefan
Schwenker, Friedhelm
MULTIPLE CLASSIFIER SYSTEMS, 2011, 6713 : 56 - 65
[25] Reinforcement learning with function approximation converges to a region
Gordon, GJ
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 13, 2001, 13 : 1040 - 1046
[26] APPROXIMATION OF THE UNIT STEP FUNCTION BY A LINEAR COMBINATION OF EXPONENTIAL FUNCTIONS
SULLIVAN, J
CRONE, L
JALICKEE, J
JOURNAL OF APPROXIMATION THEORY, 1980, 28 (04) : 299 - 308
[27] An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method
Joseph, Ajin George
Bhatnagar, Shalabh
MACHINE LEARNING, 2018, 107 (8-10) : 1385 - 1429
[28] First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
Wagenmaker, Andrew
Chen, Yifang
Simchowitz, Max
Du, Simon S.
Jamieson, Kevin
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[29] Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation
Liu, Zhishuai
Xu, Pan
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
[30] An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method
Ajin George Joseph
Shalabh Bhatnagar
Machine Learning, 2018, 107 : 1385 - 1429

← 1 2 3 4 5 →