{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T21:12:43Z","timestamp":1777497163319,"version":"3.51.4"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0111600"],"award-info":[{"award-number":["2021ZD0111600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811463"],"award-info":[{"award-number":["U1811463"]}],"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":["61836012"],"award-info":[{"award-number":["61836012"]}],"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":["U21A20470"],"award-info":[{"award-number":["U21A20470"]}],"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":["62006255"],"award-info":[{"award-number":["62006255"]}],"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":["61876224"],"award-info":[{"award-number":["61876224"]}],"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":["62206314"],"award-info":[{"award-number":["62206314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2017A030312006"],"award-info":[{"award-number":["2017A030312006"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515011835"],"award-info":[{"award-number":["2022A1515011835"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3223407","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T21:18:47Z","timestamp":1669065527000},"page":"7686-7695","source":"Crossref","is-referenced-by-count":39,"title":["Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9588-064X","authenticated-orcid":false,"given":"Changxin","family":"Huang","sequence":"first","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangrun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibo","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6107-4044","authenticated-orcid":false,"given":"Ronghui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref35","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref12","first-page":"1","article-title":"MERL: Multi-head reinforcement learning","author":"flet-berliac","year":"2019","journal-title":"Proc Int Conf Neural Inf Process Syst Deep Reinforcement Learn Workshop"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WRC-SARA.2018.8584227"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref37","article-title":"Orchestrated value mapping for reinforcement learning","author":"fatemi","year":"2022"},{"key":"ref14","article-title":"OpenAI gym","author":"brockman","year":"2016"},{"key":"ref36","article-title":"Multi-advisor reinforcement learning","author":"laroche","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1988.12075"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref11","first-page":"5392","article-title":"Hybrid reward architecture for reinforcement learning","author":"van seijen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911567"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593722"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/app9030502"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-54536-8"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2783371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2862902"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3048125"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1241826"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803333"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3182\/20100901-3-IT-2016.00302"},{"key":"ref26","first-page":"143","article-title":"DART: Noise injection for robust imitation learning","author":"laskey","year":"2017","journal-title":"Proc 1st Conf Robot Learn"},{"key":"ref25","first-page":"661","article-title":"Efficient reductions for imitation learning","author":"ross","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197175"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2405592"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2299335"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201397"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref29","first-page":"1","article-title":"Explainable reinforcement learning via reward decomposition","author":"juozapaitis","year":"2019","journal-title":"Proc IJCAI\/ECAI Workshop Explainable Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793864"},{"key":"ref7","article-title":"Hybrid zero dynamics inspired feedback control policy design for 3D bipedal locomotion using reinforcement learning","author":"castillo","year":"2019"},{"key":"ref9","article-title":"Teach biped robots to walk via gait principles and reinforcement learning with adversarial critics","author":"zhang","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912452762"},{"key":"ref3","article-title":"Dynamic humanoid locomotion: Hybrid zero dynamics based gait optimization via direct collocation methods","author":"ames","year":"2016"},{"key":"ref6","first-page":"317","article-title":"Learning locomotion skills for cassie: Iterative design and sim-to-real","author":"xie","year":"2020","journal-title":"Proc Conf Robot Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.031"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09956746.pdf?arnumber=9956746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:36:27Z","timestamp":1685381787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":38,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3223407","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}