{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T20:36:34Z","timestamp":1782506194853,"version":"3.54.5"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650769","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["CMBE: Curiosity-driven Model-Based Exploration for Multi-Agent Reinforcement Learning in Sparse Reward Settings"],"prefix":"10.1109","author":[{"given":"Kai","family":"Yang","sequence":"first","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhirui","family":"Fang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"Bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","volume":"30","author":"Tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","author":"Stadie","year":"2015","journal-title":"Incentivizing exploration in reinforcement learning with deep predictive models"},{"key":"ref4","author":"Achiam","year":"2017","journal-title":"Surprise-based intrinsic motivation for deep reinforcement learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref6","author":"Burda","year":"2018","journal-title":"Exploration by random network distillation"},{"key":"ref7","author":"Samvelyan","year":"2019","journal-title":"The starcraft multi-agent challenge"},{"key":"ref8","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"24 611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","author":"Sunehag","year":"2017","journal-title":"Value-decomposition networks for cooperative multi-agent learning"},{"issue":"1","key":"ref11","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref12","article-title":"Maven: Multi-agent variational exploration","volume":"32","author":"Mahajan","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref13","author":"Wang","year":"2020","journal-title":"Qplex: Duplex dueling multi-agent q-learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191226"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref16","author":"Kapoor","year":"2018","journal-title":"Multi-agent reinforcement learning: A report on challenges and approaches"},{"key":"ref17","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Son"},{"key":"ref18","first-page":"10 199","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5955"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/344"},{"key":"ref21","author":"Lobel","year":"2023","journal-title":"Flipping coins to estimate pseudocounts for exploration in reinforcement learning"},{"key":"ref22","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11741"},{"key":"ref24","author":"Burda","year":"2018","journal-title":"Large-scale study of curiosity-driven learning"},{"key":"ref25","author":"Yang","year":"2024","journal-title":"Exploration and anti-exploration with distributional random network distillation"},{"key":"ref26","first-page":"10 707","article-title":"Shared experience actor-critic for multi-agent reinforcement learning","volume":"33","author":"Christianos","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref28","author":"Wang","year":"2020","journal-title":"Roma: Multi-agent reinforcement learning with emergent roles"},{"key":"ref29","author":"Tao","year":"2023","journal-title":"Multi-agent exploration with sub-state entropy estimation"},{"key":"ref30","author":"Wang","year":"2019","journal-title":"Influence-based multi-agent exploration"},{"key":"ref31","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","first-page":"3757","article-title":"Episodic multi-agent reinforcement learning with curiosity-driven exploration","volume":"34","author":"Zheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref34","first-page":"21 937","article-title":"Lazy agents: a new perspective on solving sparse reward problem in multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref35","first-page":"10 041","article-title":"Maser: Multi-agent reinforcement learning with subgoals generated from experience replay buffer","volume-title":"International Conference on Machine Learning","author":"Jeon"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26384"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650769.pdf?arnumber=10650769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:59:10Z","timestamp":1725947950000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650769","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}