{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:51:46Z","timestamp":1749271906107,"version":"3.37.3"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Information and Communications Technology Planning and Evaluation (IITP) Grant"},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["2022-0-00124","2022-0-00480"],"award-info":[{"award-number":["2022-0-00124","2022-0-00480"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lcsys.2024.3405958","type":"journal-article","created":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T17:26:40Z","timestamp":1716830800000},"page":"928-933","source":"Crossref","is-referenced-by-count":1,"title":["Multiparametric Analysis of Multi-Task Markov Decision Processes: Structure, Invariance, and Reducibility"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0131-5445","authenticated-orcid":false,"given":"Jaeuk","family":"Shin","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5887-6169","authenticated-orcid":false,"given":"Insoon","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Successor features for transfer in reinforcement learning","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Barreto"},{"key":"ref2","first-page":"1","article-title":"Universal successor features approximators","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Borsa"},{"key":"ref3","first-page":"4870","article-title":"Reward-free exploration for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref4","first-page":"17816","article-title":"On reward-free reinforcement learning with linear function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref5","first-page":"1","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Eysenbach"},{"key":"ref6","first-page":"1","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sharma"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2024.3349511"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273624"},{"key":"ref9","first-page":"166","article-title":"Modular multitask reinforcement learning with policy sketches","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andreas"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683491"},{"key":"ref11","first-page":"13","article-title":"Learning one representation to optimize all rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Touati"},{"key":"ref12","first-page":"1","article-title":"Does zero-shot reinforcement learning exist?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Touati"},{"key":"ref13","first-page":"1","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Janner"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/B:JOTA.0000004869.66331.5c"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061759"},{"key":"ref16","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":"ref17","first-page":"32033","article-title":"Invariance in policy optimisation and partial identifiability in reward learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Skalse"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26766"},{"key":"ref19","first-page":"5496","article-title":"Reward identification in inverse reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref20","first-page":"1","article-title":"Quantifying differences in reward functions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gleave"},{"key":"ref21","first-page":"1","article-title":"Dynamics-aware comparison of learned reward functions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wulfe"},{"volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","year":"2014","author":"Puterman","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref24","first-page":"1094","article-title":"Learning to achieve goals","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Kaelbling"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.6.850.24925"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-0348-8438-9_1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11008-0"},{"key":"ref28","volume-title":"Convex Optimization Theory","volume":"1","author":"Bertsekas","year":"2009"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782633\/10411713\/10540067.pdf?arnumber=10540067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:39:08Z","timestamp":1729791548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10540067\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2024.3405958","relation":{},"ISSN":["2475-1456"],"issn-type":[{"type":"electronic","value":"2475-1456"}],"subject":[],"published":{"date-parts":[[2024]]}}}