{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:25:12Z","timestamp":1784643912116,"version":"3.55.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62293541"],"award-info":[{"award-number":["62293541"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62136008"],"award-info":[{"award-number":["62136008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4232056"],"award-info":[{"award-number":["4232056"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20240484514"],"award-info":[{"award-number":["20240484514"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tsmc.2024.3487535","type":"journal-article","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T18:44:15Z","timestamp":1731437055000},"page":"513-525","source":"Crossref","is-referenced-by-count":7,"title":["LDR: Learning Discrete Representation to Improve Noise Robustness in Multiagent Tasks"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9031-9889","authenticated-orcid":false,"given":"Yuqian","family":"Fu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7611-064X","authenticated-orcid":false,"given":"Jiajun","family":"Chai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref2","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Samvelyan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3213517"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3321564"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3327959"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/9781119699057.ch4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3241337"},{"key":"ref9","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref10","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893619"},{"key":"ref12","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref13","first-page":"1","article-title":"On the robustness of safe reinforcement learning under observational perturbations","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3213750"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3309608"},{"key":"ref16","first-page":"1","article-title":"Robust multi-agent reinforcement learning with model uncertainty","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3274908"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952353"},{"key":"ref19","first-page":"1","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref20","first-page":"1","article-title":"Robust reinforcement learning on state observations with learned optimal adversary","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref21","article-title":"Multi-agent deep reinforcement learning with extremely noisy observations","author":"Kilinc","year":"2018","journal-title":"arXiv:1812.00922"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SPW50608.2020.00027"},{"key":"ref23","first-page":"1","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Peng"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref27","first-page":"1","article-title":"Neural discrete representation learning","volume-title":"Proc. 31st Adv. Neural Inf. Process. Syst.","author":"van den Oord"},{"key":"ref28","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref29","first-page":"1","article-title":"Discrete compositional representations as an abstraction for goal conditioned reinforcement learning","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Islam"},{"key":"ref30","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2024","journal-title":"arXiv:2301.04104"},{"key":"ref31","first-page":"1","article-title":"Transformers are sample-efficient world models","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Micheli"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179775"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.3022698"},{"key":"ref37","first-page":"1","article-title":"The sensory neuron as a transformer: Permutation-invariant neural networks for reinforcement learning","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Tang"},{"key":"ref38","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056046"},{"key":"ref41","first-page":"1","article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3265358"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/10805216\/10750492.pdf?arnumber=10750492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:39:39Z","timestamp":1734550779000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10750492\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":43,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2024.3487535","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}