{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T04:31:53Z","timestamp":1746246713429,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102404"],"award-info":[{"award-number":["2018AAA0102404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073323"],"award-info":[{"award-number":["62073323"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA27030204,173211KYSB20200002"],"award-info":[{"award-number":["XDA27030204,173211KYSB20200002"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006469","name":"Science and Technology Development Fund of Macau","doi-asserted-by":"publisher","award":["0025\/2019\/AKP"],"award-info":[{"award-number":["0025\/2019\/AKP"]}],"id":[{"id":"10.13039\/501100006469","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9891991","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Qingxu","family":"Fu","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tenghai","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Pu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China,100049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanmai","family":"Yuan","sequence":"additional","affiliation":[{"name":"Electronics Technology Group Corporation Information Science Academy of China,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"achiam","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s12064-011-0142-z"},{"key":"ref12","article-title":"Is curiosity all you need? on the utility of emergent behaviours from curious exploration","author":"groth","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref15","article-title":"Sqil: Imitation learning via reinforcement learning with sparse rewards","author":"reddy","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref17","first-page":"1995","article-title":"Coordinated multi-agent imitation learning","author":"le","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"368","article-title":"How you act tells a lot: Privacy-leaking attack on deep reinforcement learning","author":"pan","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grand-master level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207248"},{"key":"ref5","article-title":"Episodic exploration for deep deterministic policies: An application to starcraft micromanagement tasks","author":"usunier","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Reward poisoning in reinforcement learning: Attacks against unknown learners in unknown environments","author":"rakhsha","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636636"},{"key":"ref2","article-title":"Starcraft ii: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0921-8890(95)00026-C"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09891991.pdf?arnumber=9891991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:00:55Z","timestamp":1667516455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9891991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9891991","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}