{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T16:07:56Z","timestamp":1772899676364,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Natural Science Foundation for Distinguished Young Scholars of China","doi-asserted-by":"publisher","award":["T2325018"],"award-info":[{"award-number":["T2325018"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2241228"],"award-info":[{"award-number":["U2241228"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM605"],"award-info":[{"award-number":["JYB2025XDXM605"]}]},{"DOI":"10.13039\/501100018537","name":"Shanghai Municipal Science and Technology Major Project","doi-asserted-by":"publisher","award":["25LN3200500"],"award-info":[{"award-number":["25LN3200500"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2025.3648590","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:57Z","timestamp":1768255497000},"page":"5323-5336","source":"Crossref","is-referenced-by-count":0,"title":["Evolutionary Contrastive Ensemble With Conditional Redundancy Fitness Evaluation for Goal-Conditioned Humanoid Locomotion"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4282-5687","authenticated-orcid":false,"given":"Zhiyi","family":"Shi","sequence":"first","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7713-0659","authenticated-orcid":false,"given":"Haoyu","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2600-5165","authenticated-orcid":false,"given":"Ruihao","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1301-9870","authenticated-orcid":false,"given":"Edmond Q.","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3592131"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223407"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000067"},{"key":"ref4","volume-title":"Reinforcement learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3283497"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3578229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"},{"key":"ref10","first-page":"14814","article-title":"Planning with goal-conditioned policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Nasiriany"},{"key":"ref11","article-title":"Efficient sparse-reward goal-conditioned reinforcement learning with a high replay ratio and regularization","author":"Hiraoka","year":"2023","journal-title":"arXiv:2312.05787"},{"key":"ref12","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Andrychowicz"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3107202"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2580"},{"key":"ref15","article-title":"Sample efficient deep reinforcement learning via uncertainty estimation","author":"Mai","year":"2022","journal-title":"arXiv:2201.01666"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3344880"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110975"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3113872"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561842"},{"issue":"359","key":"ref20","first-page":"1","article-title":"A unified theory of diversity in ensemble learning","volume":"24","author":"Wood","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","article-title":"Divergent ensemble networks: Enhancing uncertainty estimation with shared representations and independent branching","author":"Kharbanda","year":"2024","journal-title":"arXiv:2412.01193"},{"key":"ref22","first-page":"1","article-title":"DICE: Diversity in deep ensembles via conditional redundancy adversarial estimation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rame"},{"key":"ref23","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rafailov"},{"key":"ref24","first-page":"11428","article-title":"JAX MD: A framework for differentiable physics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schoenholz"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/COMITCon.2019.8862255"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2024.3443913"},{"key":"ref27","article-title":"Uncertainty in the variational information bottleneck","author":"Alemi","year":"2018","journal-title":"arXiv:1807.00906"},{"key":"ref28","first-page":"368","article-title":"The information bottleneck method","volume-title":"Proc. Annu. Allerton Conf. Communnication, Control Comput.","author":"Tishby"},{"key":"ref29","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belghazi"},{"key":"ref30","first-page":"13464","article-title":"Exploration via hindsight goal generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3088947"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124366"},{"key":"ref33","first-page":"7754","article-title":"Generalized hindsight for reinforcement learning","volume-title":"Proc. NIPS","author":"Li"},{"key":"ref34","article-title":"A single goal is all you need: Skills and exploration emerge from contrastive RL without rewards, demonstrations, or subgoals","author":"Liu","year":"2024","journal-title":"arXiv:2408.05804"},{"key":"ref35","article-title":"Contrastive abstraction for reinforcement learning","author":"Patil","year":"2024","journal-title":"arXiv:2410.00704"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1878"},{"key":"ref37","article-title":"Contrastive representations for temporal reasoning","author":"Ziarko","year":"2025","journal-title":"arXiv:2508.13113"},{"key":"ref38","article-title":"Contrastive difference predictive coding","author":"Zheng","year":"2023","journal-title":"arXiv:2310.20141"},{"key":"ref39","first-page":"34866","article-title":"HIQL: Offline goal-conditioned RL with latent states as actions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Park"},{"key":"ref40","first-page":"36411","article-title":"Optimal goal-reaching reinforcement learning via quasimetric learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref41","article-title":"Learning temporal distances: Contrastive successor features can provide a metric structure for decision-making","author":"Myers","year":"2024","journal-title":"arXiv:2406.17098"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089425"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3331074"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3264151"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201705"},{"key":"ref46","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref47","article-title":"The curse of diversity in ensemble-based exploration","author":"Lin","year":"2024","journal-title":"arXiv:2405.04342"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.34133\/icomputing.0025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3449726.3459475"},{"key":"ref50","first-page":"1","article-title":"Genetic soft updates for policy evolution in deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Marchesini"},{"key":"ref51","first-page":"27875","article-title":"Value-evolutionary-based reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref52","first-page":"29427","article-title":"Evorainbow: Combining improvements in evolutionary reinforcement learning for policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref53","first-page":"6651","article-title":"Evolutionary reinforcement learning for sample-efficient multiagent coordination","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Khadka"},{"key":"ref54","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref55","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref56","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sohn"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref58","first-page":"1083","article-title":"CCMI: Classifier based conditional mutual information estimation","volume-title":"Proc. Uncertainty Artif. Intell. Conf.","author":"Mukherjee"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0068580"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref61","article-title":"Accelerating goal-conditioned RL algorithms and research","author":"Micha\u0142","year":"2024","journal-title":"arXiv:2408.11052"},{"key":"ref62","first-page":"1","article-title":"Highdimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schulman"},{"key":"ref63","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11345571.pdf?arnumber=11345571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:04:28Z","timestamp":1772831068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3648590","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}