{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:32:25Z","timestamp":1730255545902,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610745","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"15076-15082","source":"Crossref","is-referenced-by-count":0,"title":["POAQL: A Partially Observable Altruistic Q-Learning Method for Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Lesong","family":"Tao","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"}]},{"given":"Miao","family":"Kang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"}]},{"given":"Jinpeng","family":"Dong","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"}]},{"given":"Songyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"}]},{"given":"Ke","family":"Ye","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"}]},{"given":"Shitao","family":"Chen","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"}]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"270","article-title":"Feasibility study: Moving non-homogeneous teams in congested video game environments","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","volume":"13","author":"Ma"},{"issue":"1","key":"ref2","first-page":"9","article-title":"Coordinating hundreds of cooperative, autonomous vehicles in warehouses","volume":"29","author":"Wurman","year":"2008","journal-title":"AI magazine"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17344"},{"article-title":"Cobots: Robust symbiotic autonomous mobile service robots","volume-title":"Twenty-fourth international joint conference on artificial intelligence","author":"Veloso","key":"ref4"},{"issue":"1","key":"ref5","first-page":"151","article-title":"Multi-agent pathfinding: Definitions, variants, and benchmarks","volume-title":"Proceedings of the International Symposium on Combinatorial Search","volume":"10","author":"Stern"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"Sunehag","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062803"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560748"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"issue":"1","key":"ref13","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":"ref14","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":"ref15","first-page":"5471","article-title":"Resq: A residual q function-based approach for multi-agent reinforcement learning value factorization","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Shen"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"article-title":"Cm3: Cooperative multi-goal multi-stage multi-agent reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Yang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"issue":"1","key":"ref19","first-page":"7382","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v8i1.18423"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2012.11.006"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"issue":"1","key":"ref23","first-page":"223","article-title":"Icbs: The improved conflict-based search algorithm for multi-agent pathfinding","volume-title":"Proceedings of the International Symposium on Combinatorial Search","volume":"6","author":"Boyarski"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v5i1.18315"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17466"},{"issue":"1","key":"ref26","first-page":"117","article-title":"Cooperative pathfinding","volume-title":"Proceedings of the aaai conference on artificial intelligence and interactive digital entertainment","volume":"1","author":"Silver"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017643"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_12"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2894217"},{"key":"ref31","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Wang"},{"article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"NIPS 2014 Workshop on Deep Learning, December 2014","author":"Chung","key":"ref32"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref33"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610745.pdf?arnumber=10610745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:20:49Z","timestamp":1723267249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610745","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}