{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:53:06Z","timestamp":1771613586419,"version":"3.50.1"},"reference-count":35,"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"}],"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651100","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":2,"title":["APC: Predict Global Representation From Local Observation In Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xiaoyang","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Department of Automation,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohua","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Department of Automation,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Department of Automation,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref2","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"issue":"746-752","key":"ref4","first-page":"2","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume":"1998","author":"Claus","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"ref5","article-title":"Multiagent planning with factored mdps","volume":"14","author":"Guestrin","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref8","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume":"35","author":"Wen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26028"},{"key":"ref10","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref11","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":"ref12","article-title":"The starcraft multi-agent challenge","author":"Samvelyan","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref14","first-page":"12208","article-title":"Facmac: Factored multi-agent centralised policy gradients","volume":"34","author":"Peng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"issue":"1","key":"ref16","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":"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":"10199","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","article-title":"Qplex: Duplex dueling multi-agent q-learning","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref20","article-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multiagent reinforcement learning","author":"Hu","year":"2021"},{"key":"ref21","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"de Witt","year":"2020"},{"key":"ref22","first-page":"24611","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":"ref23","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Kuba"},{"key":"ref24","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"International conference on machine learning","author":"He"},{"key":"ref25","first-page":"1802","article-title":"Learning policy representations in multiagent systems","volume-title":"International conference on machine learning","author":"Grover"},{"key":"ref26","first-page":"4257","article-title":"Modeling others using oneself in multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Raileanu"},{"key":"ref27","first-page":"19210","article-title":"Agent modelling under partial observability for deep reinforcement learning","volume":"34","author":"Papoudakis","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","article-title":"D2rl: Deep dense architectures in reinforcement learning","author":"Sinha","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","first-page":"1989","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","volume-title":"International Conference on Machine Learning","author":"Christianos"},{"key":"ref33","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref34","article-title":"Highdimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref35","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"}],"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\/10651100.pdf?arnumber=10651100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:27:18Z","timestamp":1725949638000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651100\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651100","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}