{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T12:36:41Z","timestamp":1753274201943,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"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":[[2023,7]]},"DOI":"10.1109\/jcc59055.2023.00007","type":"proceedings-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T17:30:29Z","timestamp":1693503029000},"page":"9-16","source":"Crossref","is-referenced-by-count":1,"title":["Bi-level Multi-Agent Actor-Critic Methods with ransformers"],"prefix":"10.1109","author":[{"given":"Tianjiao","family":"Wan","sequence":"first","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibo","family":"Mi","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Gao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzhao","family":"Zhai","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ding","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JCC56315.2022.00015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JCC56315.2022.00014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"article-title":"Towards understanding linear value decomposition in cooperative multi-agent q-learning","year":"2020","author":"Wang","key":"ref5"},{"article-title":"The starcraft multi-agent challenge","year":"2019","author":"Samvelyan","key":"ref6"},{"key":"ref7","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Rashid"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref9","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":"ref10","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":"ref11","article-title":"Unifying temporal and structural credit assignment problems","author":"Agogino","year":"2004","journal-title":"Autonomous Agents and Multi-Agent Systems Conference"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Updet: Universal multi-agent reinforcement learning via policy decoupling with transformers","year":"2021","author":"Hu","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"Sunehag","key":"ref15"},{"key":"ref16","article-title":"Hypernetworks","volume":"abs\/1609.09106","author":"Ha","year":"2016","journal-title":"CoRR"},{"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":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Wang"},{"article-title":"Qplex: Duplex dueling multi-agent q-learning","year":"2020","author":"Wang","key":"ref19"},{"key":"ref20","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"ICML","author":"Foerster","year":"2017"},{"key":"ref21","article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","volume":"abs\/1707.09183","author":"Hernandez-Leal","year":"2017","journal-title":"CoRR"},{"key":"ref22","article-title":"Multiagent cooperation and competition with deep reinforcement learning","volume":"abs\/1511.08779","author":"Tampuu","year":"2015","journal-title":"CoRR"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref23"},{"article-title":"Dop: Off-policy multi-agent decomposed policy gradients","volume-title":"International Conference on Learning Representations","author":"Wang","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17353"},{"key":"ref26","first-page":"12 208","article-title":"Facmac: Factored multi-agent centralised policy gradients","volume":"34","author":"Peng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Vain: Attentional multi-agent predictive modeling","volume":"30","author":"Hoshen","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume":"abs\/1810.02912","author":"Iqbal","year":"2018","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"Oliehoek","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref31"},{"key":"ref32","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"ICML","author":"Silver","year":"2014"},{"article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","year":"2020","author":"Papoudakis","key":"ref33"}],"event":{"name":"2023 IEEE International Conference on Joint Cloud Computing (JCC)","start":{"date-parts":[[2023,7,17]]},"location":"Athens, Greece","end":{"date-parts":[[2023,7,20]]}},"container-title":["2023 IEEE International Conference on Joint Cloud Computing (JCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10227855\/10229517\/10229625.pdf?arnumber=10229625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T22:01:54Z","timestamp":1709330514000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10229625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/jcc59055.2023.00007","relation":{},"subject":[],"published":{"date-parts":[[2023,7]]}}}