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

[41] Reinforcement learning via approximation of the Q-function
Langlois, Marina
Sloan, Robert H.
JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2010, 22 (03) : 219 - 235
[42] Exponential Stability by the Linear Approximation
N. A. Izobov
Differential Equations, 2001, 37 : 1057 - 1073
[43] Q-Learning with linear function approximation
Melo, Francisco S.
Ribeiro, M. Isabel
LEARNING THEORY, PROCEEDINGS, 2007, 4539 : 308 - +
[44] Exponential stability by the linear approximation
Izobov, NA
DIFFERENTIAL EQUATIONS, 2001, 37 (08) : 1057 - 1073
[45] When Hardness of Approximation Meets Hardness of Learning
Malach, Eran
Shalev-Shwartz, Shai
JOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23
[46] When Hardness of Approximation Meets Hardness of Learning
Malach, Eran
Shalev-Shwartz, Shai
Journal of Machine Learning Research, 2022, 23
[47] Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
Foster, Dylan J.
Krishnamurthy, Akshay
Simchi-Levi, David
Xu, Yunzong
CONFERENCE ON LEARNING THEORY, VOL 178, 2022, 178
[48] Function approximation based multi-agent reinforcement learning
Abul, O
Polat, F
Alhajj, R
12TH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2000, : 36 - 39
[49] Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Dann, Christoph
Mansour, Yishay
Mohri, Mehryar
Sekhari, Ayush
Sridharan, Karthik
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[50] Reinforcement learning algorithms with function approximation: Recent advances and applications
Xu, Xin
Zuo, Lei
Huang, Zhenhua
INFORMATION SCIENCES, 2014, 261 : 1 - 31

← 1 2 3 4 5 →