{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:22:46Z","timestamp":1740100966282,"version":"3.37.3"},"reference-count":43,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876181"],"award-info":[{"award-number":["61876181"]}],"id":[{"id":"10.13039\/501100001809","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\/ijcnn55064.2022.9892225","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":["RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Hao","family":"Chen","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}]},{"given":"Guangkai","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}]},{"given":"Junge","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}]},{"given":"Qiyue","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}]},{"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Artificial Intelligence"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Online ad hoc teamwork under partial observability","author":"gu","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref38","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","author":"long","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref33","first-page":"132","article-title":"Leading a best-response teammate in an ad hoc team","author":"stone","year":"2009","journal-title":"Agent-Mediated Electronic Commerce Designing Trading Strategies and Mechanisms for Electronic Markets"},{"key":"ref32","first-page":"341","article-title":"Leading ad hoc agents in joint action settings with multiple teammates","author":"agmon","year":"2012","journal-title":"AAMAS"},{"key":"ref31","first-page":"53","article-title":"Coordination and adaptation in impromptu teams","volume":"5","author":"bowling","year":"2005","journal-title":"AAAI"},{"key":"ref30","article-title":"Generalization in cooperative multi-agent systems","author":"mahajan","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/66"},{"key":"ref36","first-page":"567","article-title":"Empirical evaluation of ad hoc teamwork in the pursuit domain","author":"barrett","year":"2011","journal-title":"AAMAS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00103-4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1613\/jair.433"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7529"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref11","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume":"abs 1905 5408","author":"son","year":"2019","journal-title":"ArXiv"},{"key":"ref12","article-title":"Qplex: Duplex dueling multi-agent q-learning","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533636"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref15","article-title":"Graph convolutional reinforcement learning","author":"jiang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-28929-8","article-title":"A concise introduction to decentralized pomdps","author":"oliehoek","year":"2016","journal-title":"SpringerBriefs in Intelligent Systems"},{"key":"ref17","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref18","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.v33i01.3301922"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6196"},{"key":"ref4","first-page":"10757","article-title":"Multi-agent determinantal q-learning","author":"yang","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref27","first-page":"590","article-title":"Pic: permutation invariant critic for multi-agent deep reinforcement learning","author":"liu","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3058996"},{"key":"ref6","article-title":"Roma: Multi-agent reinforcement learning with emergent roles","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Multi-agent collaboration via reward attribution decomposition","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref8","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref7","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"NIPS"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"10026","DOI":"10.3390\/s150510026","article-title":"A multi-agent framework for packet routing in wireless sensor networks","volume":"15","author":"ye","year":"2015","journal-title":"SENSORS"},{"key":"ref9","article-title":"The starcraft multi-agent challenge","volume":"abs 1902 4043","author":"samvelyan","year":"2019","journal-title":"ArXiv"},{"key":"ref1","first-page":"67","article-title":"Deep multi agent reinforcement learning for autonomous driving","author":"bhalla","year":"0","journal-title":"Canadian Conference on Artificial Intelligence"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2988255"},{"key":"ref22","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Protein interface prediction using graph convolutional networks","volume":"30","author":"fout","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"0","journal-title":"AAAI Fall Symp"},{"key":"ref24","article-title":"Inductive representation learning on large graphs","volume":"30","author":"hamilton","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref41","first-page":"8776","article-title":"Towards open ad hoc teamwork using graph-based policy learning","author":"rahman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref23","article-title":"Graph attention networks","volume":"abs 1710 10903","author":"velickovic","year":"2018","journal-title":"ArXiv"},{"key":"ref26","article-title":"Counterfactual multi-agent reinforcement learning with graph convolution communication","author":"su","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref43","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","article-title":"Representation learning on graphs with jumping knowledge networks","author":"xu","year":"2018","journal-title":"ICML"}],"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\/09892225.pdf?arnumber=9892225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:26:56Z","timestamp":1667525216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892225","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}