{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T09:50:50Z","timestamp":1777110650196,"version":"3.51.4"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Robust Robot Control (DL-Force)","award":["656.000.003"],"award-info":[{"award-number":["656.000.003"]}]},{"name":"Netherlands Organisation for Scientific Research (NWO)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/lra.2018.2800101","type":"journal-article","created":{"date-parts":[[2018,1,31]],"date-time":"2018-01-31T19:19:30Z","timestamp":1517426370000},"page":"1394-1401","source":"Crossref","is-referenced-by-count":92,"title":["Integrating State Representation Learning Into Deep Reinforcement Learning"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1741-0850","authenticated-orcid":false,"given":"Tim","family":"de Bruin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7257-5434","authenticated-orcid":false,"given":"Jens","family":"Kober","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karl","family":"Tuyls","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-8598","authenticated-orcid":false,"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref31","first-page":"448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4650"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798980"},{"key":"ref11","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"0","journal-title":"Neural Inf Process Syst"},{"key":"ref12","article-title":"Loss is its own reward: Self-supervision for reinforcement learning","author":"shelhamer","year":"2016","journal-title":"CoRR"},{"key":"ref13","first-page":"5074","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"agrawal","year":"2016","journal-title":"Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317318938"},{"key":"ref15","article-title":"PVEs: Position-velocity encoders for unsupervised learning of structured state representations","author":"jonschkowski","year":"0","journal-title":"Proc New Frontiers Deep Learn Robot Workshop RSS"},{"key":"ref16","article-title":"Learning visual servoing with deep features and fitted Q-iteration","author":"lee","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022628806385"},{"key":"ref18","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"0","journal-title":"Proc Conf Artif Intell"},{"key":"ref19","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref28","first-page":"4058","article-title":"Successor features for transfer in reinforcement learning","author":"barreto","year":"2017","journal-title":"Neural Inf Process Syst"},{"key":"ref4","first-page":"372","article-title":"Multitask connectionist learning","author":"caruana","year":"0","journal-title":"Proc Connectionist Models Summer School"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref3","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proc Int Conf Mach Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref29","article-title":"Deep successor reinforcement learning","author":"kulkarni","year":"2016","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref8","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9459-7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206046"},{"key":"ref22","first-page":"1476","article-title":"Increasing the action gap: New operators for reinforcement learning","author":"bellemare","year":"2016","journal-title":"Proc Conf Artif Intell"},{"key":"ref21","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","article-title":"Gym-torcs","author":"yoshida","year":"2016"},{"key":"ref23","article-title":"TORCS, the open racing car simulator","author":"wymann","year":"0"},{"key":"ref26","first-page":"4287","article-title":"Learning values across many orders of magnitude","author":"van hasselt","year":"2016","journal-title":"Neural Inf Process Syst"},{"key":"ref25","first-page":"249","article-title":"Learning end-to-end multimodal sensor policies for autonomous navigation","author":"liu","year":"2017","journal-title":"1st Annu Conf Robot Learn CoRL"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8302435\/08276247.pdf?arnumber=8276247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:17:59Z","timestamp":1642004279000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8276247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":32,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2018.2800101","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}