{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T12:49:48Z","timestamp":1783082988679,"version":"3.54.6"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001249","name":"CoSE Incentive Grant Scheme at the University of Tasmania","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001249","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007297","name":"US Office of Naval Research Global through Cooperative Agreement","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 Discovery Early Career Researcher Award (ARC DECRA) Fellowship","doi-asserted-by":"publisher","award":["DE220100265"],"award-info":[{"award-number":["DE220100265"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/tnnls.2021.3084198","type":"journal-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T14:12:14Z","timestamp":1623247934000},"page":"5369-5378","source":"Crossref","is-referenced-by-count":58,"title":["Weak Human Preference Supervision for Deep Reinforcement Learning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3656-0328","authenticated-orcid":false,"given":"Zehong","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0510-9219","authenticated-orcid":false,"given":"KaiChiu","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8371-8197","authenticated-orcid":false,"given":"Chin-Teng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2095","article-title":"Hierarchical and non-hierarchical multi-agent interactions based on unity reinforcement learning","author":"cao","year":"2020","journal-title":"Proc 19th Int Conf Auto Agents MultiAgent Syst"},{"key":"ref11","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"2000","journal-title":"Proc ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref13","first-page":"2911","article-title":"State aware imitation learning","author":"schroecker","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.3002431"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref17","first-page":"420","article-title":"Preference learning in assistive robotics: Observational repeated inverse reinforcement learning","author":"woodworth","year":"2018","journal-title":"Proc Mach Learn Healthcare Conf"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5313-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2018.0823"},{"key":"ref28","article-title":"DeepMind control suite","author":"tassa","year":"2018","journal-title":"arXiv 1801 00690"},{"key":"ref4","article-title":"Bearing-based adaptive neural formation scaling control for autonomous surface vehicles with uncertainties and input saturation","author":"lu","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref27","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref3","first-page":"1034","article-title":"Expectation-maximization for inverse reinforcement learning with hidden data","author":"bogert","year":"2016","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0616-58"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2892926"},{"key":"ref8","article-title":"Enhancing transferability of deep reinforcement learning-based variable speed limit control using transfer learning","author":"ke","year":"2020","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"ref7","article-title":"Concrete problems in AI safety","author":"amodei","year":"2016","journal-title":"arXiv 1606 06565"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2909824.3020253"},{"key":"ref9","article-title":"Reinforcement learning from hierarchical critics","author":"cao","year":"2019","journal-title":"arXiv 1902 03079"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref22","author":"kreps","year":"1988","journal-title":"Notes on the Theory of Choice"},{"key":"ref21","first-page":"4945","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"wirth","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref24","first-page":"2760","article-title":"Model-free imitation learning with policy optimization","author":"ho","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"1133","article-title":"A Bayesian approach for policy learning from trajectory preference queries","author":"wilson","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc of USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9629429\/09448304.pdf?arnumber=9448304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:14Z","timestamp":1652194394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9448304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":28,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3084198","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]}}}