ON INFORMATION ASYMMETRY IN ONLINE REINFORCEMENT LEARNING

被引：0

作者：

Tampubolon, Ezra ^{[1
]}

Ceribasi, Haris ^{[1
]}

Boche, Holger ^{[1
,2
]}

机构：

[1] Tech Univ Munich, Lehrstuhl Theoret Informat Tech, Munich, Germany

[2] Munich Ctr Quantum Sci & Technol MCQST, Munich, Germany

来源：

2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) | 2021年

关键词：

Information Asymmetry; Q-learning; Markov Game; Reinforcement Learning; Resource Allocation; SECURITY;

D O I：

10.1109/ICASSP39728.2021.9413968

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this work, we study the system of two interacting non-cooperative Q-learning agents, where one agent has the privilege of observing the other's actions. We show that this information asymmetry can lead to a stable outcome of population learning, which does not occur in an environment of general independent learners. Furthermore, we discuss the resulted post-learning policies, show that they are almost optimal in the underlying game sense, and provide numerical hints of almost welfare-optimal of the resulted policies.

引用

页码：4955 / 4959

页数：5

共 50 条

[21] Optimization of Learning Cycles in Online Reinforcement Learning Systems
Notsu, Akira
Yasuda, Koji
Ubukata, Seiki
Honda, Katsuhiro
2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2018, : 3530 - 3534
[22] Information Directed Reward Learning for Reinforcement Learning
Lindner, David
Turchetta, Matteo
Tschiatschek, Sebastian
Ciosek, Kamil
Krause, Andreas
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[23] Information asymmetry and small business in online auction market
Sun, Chia-Hung
Liu, Kang E.
SMALL BUSINESS ECONOMICS, 2010, 34 (04) : 433 - 444
[24] Information asymmetry and small business in online auction market
Chia-Hung Sun
Kang E. Liu
Small Business Economics, 2010, 34 : 433 - 444
[25] Intelligent Online Traffic Optimization Based on Deep Reinforcement Learning for Information-Centric Networks
Yu, Hongzhi
Qian, Xingxin
Qin, Guangyi
Ren, Jing
Wang, Xiong
EMERGING NETWORKING ARCHITECTURE AND TECHNOLOGIES, ICENAT 2022, 2023, 1696 : 598 - 613
[26] Quasi-online reinforcement learning for robots
Bakker, Bram
Zhumatiy, Viktor
Gruener, Gabriel
Schmidhuber, Juergen
2006 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-10, 2006, : 2997 - +
[27] Reducing reinforcement learning to KWIK online regression
Li, Lihong
Littman, Michael L.
ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE, 2010, 58 (3-4) : 217 - 237
[28] Online inverse reinforcement learning with limited data
Self, Ryan
Mahmud, S. M. Nahid
Hareland, Katrine
Kamalapurkar, Rushikesh
2020 59TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2020, : 603 - 608
[29] Efficient Online Reinforcement Learning with Offline Data
Ball, Philip J.
Smith, Laura
Kostrikov, Ilya
Levine, Sergey
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, 2023, 202
[30] Reinforcement learning for online control of evolutionary algorithms
Eiben, A. E.
Horvath, Mark
Kowalczyk, Wojtek
Schut, Martijn C.
ENGINEERING SELF-ORGANISING SYSTEMS, 2007, 4335 : 151 - +

← 1 2 3 4 5 →