On convergence rates of game theoretic reinforcement learning algorithms

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' action sets, their deployed actions or the structures of its own or the others' utility functions. Instead, each player o...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-12
Main Authors: Hu, Zhisheng, Zhu, Minghui, Chen, Ping, Liu, Peng
Format: Article
Language:English
Subjects:
Algorithms
Convergence
Cybersecurity
Game theory
Machine learning
Smart grid
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Hu, Zhisheng
Zhu, Minghui
Chen, Ping
Liu, Peng
description 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' action sets, their deployed actions or the structures of its own or the others' 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, the convergence rate of the proposed algorithm is quantified. The algorithm performance is verified using two case studies in the smart grid and cybersecurity.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2076460931</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2076460931</sourcerecordid><originalsourceid>FETCH-proquest_journals_20764609313</originalsourceid><addsrcrecordid>eNqNyr0KwjAUQOEgCBbtO1xwLqRJf3QWpZuLewnhNk1pb_Qm9fl18AGczvCdjciU1mVxqpTaiTzGSUqpmlbVtc5Edyewgd7IDskisEkYIQzgzIKQRgyMyVtg9DQEtrggJZjRMHlyYGYX2KdxiQexHcwcMf91L4636-PSFU8OrxVj6qewMn2pV7Jtqkaedan_uz6NJzy1</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2076460931</pqid></control><display><type>article</type><title>On convergence rates of game theoretic reinforcement learning algorithms</title><source>Publicly Available Content Database</source><creator>Hu, Zhisheng ; Zhu, Minghui ; Chen, Ping ; Liu, Peng</creator><creatorcontrib>Hu, Zhisheng ; Zhu, Minghui ; Chen, Ping ; Liu, Peng</creatorcontrib><description>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' action sets, their deployed actions or the structures of its own or the others' 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, the convergence rate of the proposed algorithm is quantified. The algorithm performance is verified using two case studies in the smart grid and cybersecurity.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Convergence ; Cybersecurity ; Game theory ; Machine learning ; Smart grid</subject><ispartof>arXiv.org, 2017-12</ispartof><rights>2017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2076460931?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Hu, Zhisheng</creatorcontrib><creatorcontrib>Zhu, Minghui</creatorcontrib><creatorcontrib>Chen, Ping</creatorcontrib><creatorcontrib>Liu, Peng</creatorcontrib><title>On convergence rates of game theoretic reinforcement learning algorithms</title><title>arXiv.org</title><description>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' action sets, their deployed actions or the structures of its own or the others' 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, the convergence rate of the proposed algorithm is quantified. The algorithm performance is verified using two case studies in the smart grid and cybersecurity.</description><subject>Algorithms</subject><subject>Convergence</subject><subject>Cybersecurity</subject><subject>Game theory</subject><subject>Machine learning</subject><subject>Smart grid</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNyr0KwjAUQOEgCBbtO1xwLqRJf3QWpZuLewnhNk1pb_Qm9fl18AGczvCdjciU1mVxqpTaiTzGSUqpmlbVtc5Edyewgd7IDskisEkYIQzgzIKQRgyMyVtg9DQEtrggJZjRMHlyYGYX2KdxiQexHcwcMf91L4636-PSFU8OrxVj6qewMn2pV7Jtqkaedan_uz6NJzy1</recordid><startdate>20171202</startdate><enddate>20171202</enddate><creator>Hu, Zhisheng</creator><creator>Zhu, Minghui</creator><creator>Chen, Ping</creator><creator>Liu, Peng</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20171202</creationdate><title>On convergence rates of game theoretic reinforcement learning algorithms</title><author>Hu, Zhisheng ; Zhu, Minghui ; Chen, Ping ; Liu, Peng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20764609313</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Algorithms</topic><topic>Convergence</topic><topic>Cybersecurity</topic><topic>Game theory</topic><topic>Machine learning</topic><topic>Smart grid</topic><toplevel>online_resources</toplevel><creatorcontrib>Hu, Zhisheng</creatorcontrib><creatorcontrib>Zhu, Minghui</creatorcontrib><creatorcontrib>Chen, Ping</creatorcontrib><creatorcontrib>Liu, Peng</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hu, Zhisheng</au><au>Zhu, Minghui</au><au>Chen, Ping</au><au>Liu, Peng</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>On convergence rates of game theoretic reinforcement learning algorithms</atitle><jtitle>arXiv.org</jtitle><date>2017-12-02</date><risdate>2017</risdate><eissn>2331-8422</eissn><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' action sets, their deployed actions or the structures of its own or the others' 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, the convergence rate of the proposed algorithm is quantified. The algorithm performance is verified using two case studies in the smart grid and cybersecurity.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2017-12
issn 2331-8422
language eng
recordid cdi_proquest_journals_2076460931
source Publicly Available Content Database
subjects Algorithms
Convergence
Cybersecurity
Game theory
Machine learning
Smart grid
title On convergence rates of game theoretic reinforcement learning algorithms
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T00%3A27%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=On%20convergence%20rates%20of%20game%20theoretic%20reinforcement%20learning%20algorithms&rft.jtitle=arXiv.org&rft.au=Hu,%20Zhisheng&rft.date=2017-12-02&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2076460931%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20764609313%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2076460931&rft_id=info:pmid/&rfr_iscdi=true