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 31 条

[1] Information asymmetry, R&D, and insider gains
Aboody, D
Lev, B
[J]. JOURNAL OF FINANCE, 2000, 55 (06) : 2747 - 2766
[2] Adlakha S., 2013, COMPETITION WIRELESS, P32
[3] Amiri R, 2018, IEEE ICC
[4] [Anonymous], 2010, Network Security: A Decision and Game-Theoretic Approach
[5] Decentralized Q-Learning for Stochastic Teams and Games
Arslan, Gurdal
Yuksel, Serdar
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2017, 62 (04) : 1545 - 1558
[6] Bennis M., 2010, 2010 IEEE Globecom Workshops (GC'10), P706, DOI 10.1109/GLOCOMW.2010.5700414
[7] Learning Radio Resource Management in RANs: Framework, Opportunities, and Challenges
Calabrese, Francesco Davide
Wang, Li
Ghadimi, Euhanna
Peters, Gunnar
Hanzo, Lajos
Soldati, Pablo
[J]. IEEE COMMUNICATIONS MAGAZINE, 2018, 56 (09) : 138 - 145
[8] Claus C, 1998, FIFTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-98) AND TENTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICAL INTELLIGENCE (IAAI-98) - PROCEEDINGS, P746
[9] Dynamic Games in Cyber-Physical Security: An Overview
Etesami, S. Rasoul
Basar, Tamer
[J]. DYNAMIC GAMES AND APPLICATIONS, 2019, 9 (04) : 884 - 913
[10] Ghadimi E., 2017, 2017 IEEE INT C COMM, P1

← 1 2 3 4 →