{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:19:18Z","timestamp":1759335558159,"version":"3.37.3"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association CAS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191833","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Underexplored Subspace Mining for Sparse-Reward Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yang","family":"Yu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiyue","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junge","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"bellemare","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390288"},{"key":"ref15","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","author":"liu","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref14","article-title":"Exploration by random network distillation","author":"burda","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref30","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139645"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5870"},{"key":"ref32","article-title":"Emi: Exploration with mutual information","author":"kim","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref16","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"rashid","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2012.6195556"},{"key":"ref24","article-title":"The surprising effectiveness of mappo in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"Learning implicit credit assignment for multi-agent actor-critic","author":"zhou","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref26","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":"ref25","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref20","article-title":"Qplex: Duplex dueling multi-agent q-learning","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref21","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Ride: Rewarding impact-driven exploration for procedurally-generated environments","author":"raileanu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Coordinated exploration via intrinsic rewards for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"7613","article-title":"Maven: Multi-agent variational exploration","volume":"32","author":"mahajan","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1266"},{"key":"ref4","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"h\u00fcttenrauch","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref6","article-title":"Influence-based multi-agent exploration","author":"wang","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref5","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","author":"jaques","year":"2019","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191833.pdf?arnumber=10191833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:47:29Z","timestamp":1692640049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191833","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}