{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:27:25Z","timestamp":1740101245681,"version":"3.37.3"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100016047","name":"Science Fund of the Republic of Serbia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100016047","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992951","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"4591-4596","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Agent Actor-Critic Multitask Reinforcement Learning based on GTD(1) with Consensus"],"prefix":"10.1109","author":[{"given":"Milos S.","family":"Stankovic","sequence":"first","affiliation":[{"name":"University Singidunum,Belgrade,Serbia"}]},{"given":"Marko","family":"Beko","sequence":"additional","affiliation":[{"name":"Universidade de Lisboa,Instituto de Telecomunicações, Instituto Superior Técnico,Lisbon,Portugal"}]},{"given":"Nemanja","family":"Ilic","sequence":"additional","affiliation":[{"name":"College of Applied Technical Sciences,Kruševac,Serbia"}]},{"given":"Srdjan S.","family":"Stankovic","sequence":"additional","affiliation":[{"name":"University of Belgrade,School of Electrical Engineering,Serbia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/s0363012901385691"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref5","first-page":"179","article-title":"Off policy actor critic","volume-title":"Proc. Int. Conf. Machine Learning","author":"Degris"},{"key":"ref6","first-page":"3426","article-title":"Actor-critic policy optimization in partially observable multiagent environments","author":"Srinavasan","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Convergent actor-critic algorithms under off-policy training and function approximation","year":"2018","author":"Maei","key":"ref7"},{"key":"ref8","first-page":"96","article-title":"An off-policy gradient theorem using emphatic weightings","volume-title":"Proc. Advances in Neural Information Processing Systems 2018","volume":"31","author":"Imani"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3061909"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683607"},{"key":"ref11","first-page":"1626","article-title":"Finite-time analysis of distributed TD(0) with linear function approximation on multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Machine Learning","author":"Doan"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619839"},{"key":"ref13","first-page":"1002","article-title":"A decentralized policy gradient approach to multi-task reinforcement learning","volume-title":"Proc. 37th Conference on Uncertainty in Artificial Intelligence","author":"Zeng"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2021"},{"volume-title":"Multiple criteria optimization: theory, computation and applications.","year":"1986","author":"Steuer","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.1900661"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2037462"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029969"},{"article-title":"Diff-DAC: Distributed actor-critic for average multitask deep reinforcement learning","year":"2019","author":"Valcarcel Macua","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CoDIT55151.2022.9804022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2016.2633788"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.07.018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2012.01.007"},{"article-title":"On convergence of some gradient-based temporal-differences algorithms for off-policy learning","year":"2017","author":"Yu","key":"ref26"},{"key":"ref27","first-page":"289","article-title":"Off-policy learning with eligibility traces: A survey","volume":"15","author":"Geist","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996209"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2174\/156720181901220120094538"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2545098"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/0325070"},{"key":"ref32","first-page":"1724","article-title":"On convergence of emphatic temporal-difference learning","volume":"40","author":"Yu","year":"2015"},{"key":"ref33","first-page":"1","article-title":"Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize","volume":"17","author":"Yu","year":"2016","journal-title":"Journal of Machine Learning Research"},{"volume-title":"Stochastic Approximation and Recursive Algorithms and Applications.","year":"2003","author":"Kushner","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1090\/mmono\/047"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)90015-3"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","start":{"date-parts":[[2022,12,6]]},"location":"Cancun, Mexico","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992951.pdf?arnumber=9992951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T09:32:50Z","timestamp":1709371970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992951","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}