@article{02446a0f3187430d873c0c44bc78ac1e,
title = "On convergence rates of game theoretic reinforcement learning algorithms",
abstract = "This paper investigates a class of multi-player discrete games where each player aims to maximize its own utility function. Each player does not know the other players{\textquoteright} action sets, their deployed actions or the structures of its own or the others{\textquoteright} utility functions. Instead, each player only knows its own deployed actions and its received utility values in recent history. We propose a reinforcement learning algorithm which converges to the set of action profiles which have maximal stochastic potential with probability one. Furthermore, an upper bound on the convergence rate is derived and is minimized when the exploration rates are restricted to p-series. The algorithm performance is verified using a case study in the smart grid.",
author = "Zhisheng Hu and Minghui Zhu and Ping Chen and Peng Liu",
note = "Funding Information: Z. Hu and M. Zhu were partially supported by ARO, United StatesW911NF-13-1-0421 (MURI), NSA, United StatesH98230-15-1-0289 and National Science Foundation (NSF), United StatesECCS-1710859. P. Chen and P. Liu were partially supported by ARO, United StatesW911NF-13-1-0421 (MURI) and National Science Foundation (NSF), United StatesCNS-1422594. The material in this paper was partially presented at the First ACM Workshop on Moving Target Defense, in conjunction with 2014 ACM Conference on Computer and Communications Security, November 3, 2014, Scottsdale, Arizona, USA. This paper was recommended for publication in revised form by Associate Editor Gurdal Arslan under the direction of Editor Ian R. Petersen. Funding Information: Peng Liu received his BS and MS degrees from the University of Science and Technology of China, and his Ph.D. from George Mason University in 1999. Dr. Liu is the Raymond G. Tronzo, M.D. Professor of Cybersecurity, founding Director of the Center for Cyber-Security, Information Privacy, and Trust, and founding Director of the Cyber Security Lab at Penn State University. His research interests are in all areas of computer security. He has published numerous papers in top conferences and journals. His research has been sponsored by NSF, ARO, AFOSR, DARPA, DHS, DOE, AFRL, NSA, TTC, CISCO, and HP. He has served as a program (co-)chair or general (co-)chair for over 10 international conferences (e.g., Asia CCS 2010) and workshops (e.g., MTD 2016). He chaired the Steering Committee of SECURECOMM during 2008–14. He has served in over 100 program committees and reviewed papers for numerous journals. He is an associate editor for IEEE TDSC. He is a recipient of the DOE Early Career Principle Investigator Award. He has co-led the effort to make Penn State a NSA-certified National Center of Excellence in Information Assurance Education and Research. He has advised or co-advised over 35 Ph.D. dissertations to completion. Publisher Copyright: {\textcopyright} 2019 Elsevier Ltd",
year = "2019",
month = jun,
doi = "10.1016/j.automatica.2019.02.032",
language = "English (US)",
volume = "104",
pages = "90--101",
journal = "Automatica",
issn = "0005-1098",
publisher = "Elsevier Limited",
}
