{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T20:38:35Z","timestamp":1793911115882,"version":"4.8.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/tdmrep.html"}],"funder":[{"name":"National Natural Science Foundation of China","id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/icarm62033.2024.10715850","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T13:27:32Z","timestamp":1729258052000},"page":"721-728","source":"Crossref","is-referenced-by-count":0,"title":["Task-Oriented Reinforcement Learning with Interest State Representation"],"prefix":"10.1109","author":[{"given":"Ziyi","family":"Li","sequence":"first","affiliation":[{"name":"Anhui University","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangtao","family":"Hu","sequence":"additional","affiliation":[{"name":"Anhui University","place":["Hefei, China"],"department":["Department of Electrical Engineering and Automation"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongle","family":"Zhang","sequence":"additional","affiliation":[{"name":"Anhui University","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fujie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Anhui University","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3259681"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3227873"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140817"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2019.8816481"},{"key":"ref5","article-title":"S-rl toolbox: Environments, datasets and evaluation metrics for state representation learning","author":"Raffin","year":"2018","journal-title":"arXiv preprint arXiv:1809.09369"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-024-11650-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR58764.2023.10249999"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3082947"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref12","article-title":"Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics","author":"Raffin","year":"2019","journal-title":"arXiv preprint arXiv:1901.08651"},{"key":"ref13","first-page":"741","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume":"33","author":"Lee","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9459-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS52745.2021.9649826"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95892-3_41"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3172754"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981863"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004255"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref21","first-page":"501","article-title":"Transfer in deep reinforcement learning using successor features and generalised policy improvement","volume-title":"International Conference on Machine Learning. PMLR","author":"Barreto"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref24","article-title":"Universal successor features for transfer reinforcement learning","author":"Ma","year":"2020","journal-title":"arXiv preprint arXiv:2001.04025"},{"key":"ref25","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Gupta"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139807"}],"event":{"name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","location":"Tokyo, Japan","start":{"date-parts":[[2024,7,8]]},"end":{"date-parts":[[2024,7,10]]}},"container-title":["2024 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10715684\/10715739\/10715850.pdf?arnumber=10715850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T20:15:03Z","timestamp":1793909703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10715850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icarm62033.2024.10715850","relation":{},"subject":[],"published":{"date-parts":[[2024,7]]}}}