{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:59:54Z","timestamp":1778255994563,"version":"3.51.4"},"reference-count":30,"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\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","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\/smc42975.2020.9283339","type":"proceedings-article","created":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T21:44:48Z","timestamp":1607982288000},"page":"3013-3020","source":"Crossref","is-referenced-by-count":8,"title":["AHAC: Actor Hierarchical Attention Critic for Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yajie","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dianxi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongju","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref11","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"0"},{"key":"ref12","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref15","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"2017"},{"key":"ref16","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2014"},{"key":"ref18","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref19","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017"},{"key":"ref28","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents","author":"tan","year":"1993","journal-title":"Proceedings of the Tenth International Conference on Machine Learning"},{"key":"ref27","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/978-3-642-14435-6_7","article-title":"Multi-agent reinforcement? learning: An overview","author":"bus\u00b8oniu","year":"2010","journal-title":"Innovations in Multi-Agent Systems and Applications - 1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref2","article-title":"Multiagent reinforcement learning for multi-robot systems: A survey","author":"yang","year":"2004"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"2017","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Multi-agent game abstraction via graph attention neural network","author":"liu","year":"2019"},{"key":"ref21","first-page":"7254","article-title":"Learning attentional communication for multi-agent cooperation","author":"jiang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Control of memory, active perception, and action in minecraft","author":"oh","year":"2016"},{"key":"ref23","article-title":"Neural turing machines","author":"graves","year":"2014"},{"key":"ref26","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref25","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","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\/09283339.pdf?arnumber=9283339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T22:55:41Z","timestamp":1670194541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9283339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,11]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/smc42975.2020.9283339","relation":{},"subject":[],"published":{"date-parts":[[2020,10,11]]}}}