{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T02:57:42Z","timestamp":1729652262052,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/case48305.2020.9216877","type":"proceedings-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T16:01:51Z","timestamp":1602172911000},"page":"1257-1262","source":"Crossref","is-referenced-by-count":4,"title":["A Soft Graph Attention Reinforcement Learning for Multi-Agent Cooperation"],"prefix":"10.1109","author":[{"given":"Huimu","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Pu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tenghai","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"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":"5567","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref12","first-page":"7254","article-title":"Learning attentional communication for multiagent cooperation","author":"jiang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref14","first-page":"1538","article-title":"Tarmac: Targeted multi-agent communication","author":"das","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref15","article-title":"Deep multi-agent reinforcement learning with relevance graphs","author":"malysheva","year":"2018","journal-title":"arXiv preprint arXiv 1811 12557"},{"key":"ref16","article-title":"Graph convolutional reinforcement learning for multi-agent cooperation","volume":"2","author":"jiang","year":"2018","journal-title":"arXiv preprint arXiv 1810 06008"},{"key":"ref17","article-title":"Learning transferable cooperative behavior in multi-agent teams","author":"agarwal","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref18","article-title":"Graph attention networks","author":"veli?kovi?","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref6","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref8","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv preprint arXiv 1707 00666"},{"key":"ref7","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref2","first-page":"980","article-title":"A cooperative multi-agent reinforcement learning framework for resource balancing in complex logistics network","author":"li","year":"2019","journal-title":"Int Conf Auton Agents Multiagent syst International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2016.02.117"},{"key":"ref9","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"}],"event":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2020,8,20]]},"location":"Hong Kong, Hong Kong","end":{"date-parts":[[2020,8,21]]}},"container-title":["2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9210430\/9216730\/09216877.pdf?arnumber=9216877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T12:59:54Z","timestamp":1669121994000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9216877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/case48305.2020.9216877","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}