{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T18:31:40Z","timestamp":1785522700275,"version":"3.56.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T00:00:00Z","timestamp":1602374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T00:00:00Z","timestamp":1602374400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,11]],"date-time":"2020-10-11T00:00:00Z","timestamp":1602374400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,11]]},"DOI":"10.1109\/smc42975.2020.9283355","type":"proceedings-article","created":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T21:44:48Z","timestamp":1607982288000},"page":"629-634","source":"Crossref","is-referenced-by-count":5,"title":["Learning Effective Value Function Factorization via Attentional Communication"],"prefix":"10.1109","author":[{"given":"Bo","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoya","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuxiong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"5998","article-title":"Attention is all you need[C]","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1049\/cp:19991218","article-title":"Learning to forget: Continual prediction with LSTM[J]","author":"gers","year":"1999"},{"key":"ref30","article-title":"Deep recurrent q-learning for partially observable mdps[C]","author":"hausknecht","year":"2015","journal-title":"2015 AAAI Fall Symposium Series"},{"key":"ref35","article-title":"Influence-Based Multi-Agent Exploration[J]","author":"wang","year":"2019"},{"key":"ref34","article-title":"Hypernetworks[J]","author":"ha","year":"2016"},{"key":"ref10","article-title":"Building generalizable agents with a realistic and rich 3d environment[J]","author":"wu","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients[C]","author":"foerster","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref13","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments[C]","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Playing atari with deep reinforcement learning[J]","author":"mnih","year":"2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning[C]","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref18","article-title":"Value-decomposition networks for cooperative multi-agent learning[J]","author":"sunehag","year":"2017"},{"key":"ref19","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning[J]","author":"rashid","year":"2018"},{"key":"ref28","article-title":"Emergent translation in multi-agent communication[J]","author":"lee","year":"2017"},{"key":"ref4","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games[J]","author":"peng","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1224"},{"key":"ref3","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning[C]","volume":"2016","author":"foerster","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Tarmac: Targeted multi-agent com- munication[J]","author":"das","year":"2018"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-28929-8","article-title":"A concise introduction to decentralized POMDPs[M]","author":"oliehoek","year":"2016"},{"key":"ref5","first-page":"7254","article-title":"Learning attentional communication for multi-agent cooperation[C]","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents[C]","author":"tan","year":"1993"},{"key":"ref7","first-page":"2186","article-title":"The starcraft multi-agent challenge[C]","author":"samvelyan","year":"2019","journal-title":"Int Conf Auton Agents Multiagent syst International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref2","first-page":"2244","article-title":"Learning multiagent communication with back-propagation[C]","author":"sukhbaatar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks[J]","author":"singh","year":"2018"},{"key":"ref1","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning[J]","author":"son","year":"2019"},{"key":"ref20","first-page":"3230","article-title":"Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control[C]","author":"zhang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Infobot: Transfer and exploration via the information bottleneck[J]","author":"goyal","year":"2019"},{"key":"ref21","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning[J]","author":"jaques","year":"2018"},{"key":"ref24","article-title":"Multi-agent cooperation and the emergence of (natural) language[J]","author":"lazaridou","year":"2016"},{"key":"ref23","article-title":"Learning Nearly Decomposable Value Functions Via Communication Minimization[J]","author":"wang","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1321"},{"key":"ref25","first-page":"2149","article-title":"Emergence of language with multi-agent games: Learning to communicate with sequences of symbols[C]","author":"havrylov","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Toronto, ON, Canada","start":{"date-parts":[[2020,10,11]]},"end":{"date-parts":[[2020,10,14]]}},"container-title":["2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9282733\/9282811\/09283355.pdf?arnumber=9283355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T22:57:13Z","timestamp":1670194633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9283355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,11]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/smc42975.2020.9283355","relation":{},"subject":[],"published":{"date-parts":[[2020,10,11]]}}}