{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T05:34:29Z","timestamp":1776404069717,"version":"3.51.2"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007297","name":"U.S. Office of Naval Research Global","doi-asserted-by":"publisher","award":["ONRG-NICOP-N62909-19-1-2058"],"award-info":[{"award-number":["ONRG-NICOP-N62909-19-1-2058"]}],"id":[{"id":"10.13039\/100007297","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP180100656"],"award-info":[{"award-number":["DP180100656"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210101093"],"award-info":[{"award-number":["DP210101093"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"US Air Force Office of Scientific Research (AFOSR) and Defence Science and Technology (DST) Australian Autonomy Initiative","doi-asserted-by":"publisher","award":["ID10134"],"award-info":[{"award-number":["ID10134"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Dr. Cao ARC DECRA Fellowship","award":["DE220100265"],"award-info":[{"award-number":["DE220100265"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/tnnls.2021.3103642","type":"journal-article","created":{"date-parts":[[2021,8,25]],"date-time":"2021-08-25T19:49:46Z","timestamp":1629920986000},"page":"1066-1073","source":"Crossref","is-referenced-by-count":11,"title":["Reinforcement Learning From Hierarchical Critics"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3656-0328","authenticated-orcid":false,"given":"Zehong","family":"Cao","sequence":"first","affiliation":[{"name":"STEM, University of South Australia, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8371-8197","authenticated-orcid":false,"given":"Chin-Teng","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science, Australian Artificial Intelligence Institute (AAII), University of Technology Sydney, Sydney, NSW, Australia"}],"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","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"ref3","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"arXiv:1803.11485","author":"Rashid","year":"2018"},{"key":"ref4","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref6","first-page":"13485","article-title":"Exploration via hindsight goal generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref7","first-page":"1","article-title":"Learning multi-level hierarchies with hindsight","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Levy"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref9","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Vezhnevets"},{"key":"ref10","article-title":"Feudal multi-agent hierarchies for cooperative reinforcement learning","volume-title":"arXiv:1901.08492","author":"Ahilan","year":"2019"},{"key":"ref11","first-page":"3307","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref12","first-page":"1","article-title":"Hierarchical reinforcement learning via advantage-weighted information maximization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Osa"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553495"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv:1509.02971","author":"Lillicrap","year":"2015"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref18","article-title":"Unity: A general platform for intelligent agents","volume-title":"arXiv:1809.02627","author":"Juliani","year":"2018"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10036162\/09521974.pdf?arnumber=9521974","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:11:09Z","timestamp":1706058669000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9521974\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":18,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3103642","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}