{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T21:28:57Z","timestamp":1777411737529,"version":"3.51.4"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306088"],"award-info":[{"award-number":["62306088"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["YQ2024007"],"award-info":[{"award-number":["YQ2024007"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Songjiang Laboratory","award":["SL20230309"],"award-info":[{"award-number":["SL20230309"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3554861","type":"journal-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:07:38Z","timestamp":1743044858000},"page":"13728-13740","source":"Crossref","is-referenced-by-count":5,"title":["Auxiliary Reward Generation With Transition Distance Representation Learning"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7965-598X","authenticated-orcid":false,"given":"Siyuan","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4780-3815","authenticated-orcid":false,"given":"Shijie","family":"Han","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5037-8813","authenticated-orcid":false,"given":"Yingnan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8748-1964","authenticated-orcid":false,"given":"Yiqin","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianchuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Systems Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6568-1335","authenticated-orcid":false,"given":"Peng","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11741"},{"key":"ref4","article-title":"Hierarchical reinforcement learning with advantage-based auxiliary rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref5","article-title":"Reward shaping via meta-learning","author":"Zou","year":"2019","journal-title":"arXiv:1901.09330"},{"key":"ref6","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref8","first-page":"566","article-title":"Source task creation for curriculum learning","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Narvekar"},{"key":"ref9","first-page":"1026","article-title":"Object-oriented curriculum generation for reinforcement learning","volume-title":"Proc. 17th Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Silva"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/671"},{"key":"ref11","first-page":"41","article-title":"Learning a distance metric from relative comparisons","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"16","author":"Schultz"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-6419.2011.00715.x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206234"},{"key":"ref14","article-title":"Eureka: Human-level reward design via coding large language models","author":"Ma","year":"2023","journal-title":"arXiv:2310.12931"},{"key":"ref15","article-title":"Reward design with language models","volume-title":"arXiv:2303.00001","author":"Kwon","year":"2023"},{"key":"ref16","article-title":"Text2Reward: Reward shaping with language models for reinforcement learning","author":"Xie","year":"2023","journal-title":"arXiv:2309.11489"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref20","first-page":"25117","article-title":"Mask-based latent reconstruction for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu"},{"key":"ref21","article-title":"From pixels to torques: Policy learning with deep dynamical models","author":"Wahlstr\u00f6m","year":"2015","journal-title":"arXiv:1502.02251"},{"key":"ref22","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Watter"},{"key":"ref23","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hafner"},{"key":"ref24","first-page":"741","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Lee"},{"key":"ref25","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023","journal-title":"arXiv:2301.04104"},{"key":"ref26","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henaff"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref29","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref31","first-page":"48203","article-title":"TACO: Temporal latent action-driven contrastive loss for visual reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zheng"},{"key":"ref32","first-page":"35603","article-title":"Contrastive learning as goal-conditioned reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Eysenbach"},{"key":"ref33","article-title":"Learning subgoal representations with slow dynamics","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref34","first-page":"39183","article-title":"Behavior contrastive learning for unsupervised skill discovery","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref35","article-title":"CIC: Contrastive intrinsic control for unsupervised skill discovery","author":"Laskin","year":"2022","journal-title":"arXiv:2202.00161"},{"key":"ref36","first-page":"1015","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"22","author":"Konidaris"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9081295"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.112"},{"key":"ref39","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref41","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref42","first-page":"11761","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar"},{"key":"ref43","article-title":"Robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020","journal-title":"arXiv:2009.12293"},{"key":"ref44","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref45","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.035"},{"issue":"11","key":"ref47","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3398300"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10942400.pdf?arnumber=10942400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,19]],"date-time":"2025-04-19T04:31:13Z","timestamp":1745037073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10942400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3554861","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}