{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:40:52Z","timestamp":1776886852283,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095374","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Hierarchical Multi-Agent Reinforcement Learning with Intrinsic Reward Rectification"],"prefix":"10.1109","author":[{"given":"Zhihao","family":"Liu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Fusion Innovation Center, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Fusion Innovation Center, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoliang","family":"Fan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Fusion Innovation Center, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref2","first-page":"1566","article-title":"Hierarchical cooperative multi-agent reinforcement learning with skill discovery","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems","author":"Yang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014691"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87479-9_61"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref6","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"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","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multiagent reinforcement learning","volume-title":"International conference on machine learning","author":"Son"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26386"},{"key":"ref10","article-title":"The starcraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref12","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Vezhnevets"},{"key":"ref13","article-title":"Feudal multiagent hierarchies for cooperative reinforcement learning","author":"Ahilan","year":"2019"},{"key":"ref14","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"Kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/482"},{"key":"ref17","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"ArXiv"},{"key":"ref18","article-title":"Rode: Learning roles to decompose multi-agent tasks","author":"Wang","year":"2020"},{"key":"ref19","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":"ref20","article-title":"Maven: Multi-agent variational exploration","volume":"32","author":"Mahajan","year":"2019","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095374.pdf?arnumber=10095374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:21:22Z","timestamp":1705026082000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095374","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}