{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:49:43Z","timestamp":1732042183012,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956553","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:34:13Z","timestamp":1669732453000},"page":"2172-2178","source":"Crossref","is-referenced-by-count":1,"title":["Temporal Alignment for History Representation in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Aleksandr","family":"Ermolov","sequence":"first","affiliation":[{"name":"University of Trento,Department of Information Engineering and Computer Science (DISI),Italy"}]},{"given":"Enver","family":"Sangineto","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio,Department of Engineering (DIEF),Emilia,Italy"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"University of Trento,Department of Information Engineering and Computer Science (DISI),Italy"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.465"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317318938"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref35","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","year":"2014","author":"saxe","key":"ref34"},{"key":"ref10","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.28.1.1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"article-title":"Deep recurrent q-learning for partially observable mdps","year":"0","author":"hausknecht","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref17","first-page":"2117","article-title":"Deep variational reinforcement learning for pomdps","author":"igl","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref19","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"grill","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Mastering atari games with limited data","volume":"34","author":"ye","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref27","first-page":"5565","article-title":"Latent world models for intrinsically motivated exploration","volume":"33","author":"ermolov","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Recurrent experience replay in distributed reinforcement learning","author":"kapturowski","year":"2019","journal-title":"ICLRE"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"oord","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref5","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"ICLRE"},{"key":"ref8","article-title":"Unsupervised state representation learning in atari","volume":"32","author":"anand","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_33"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03544-w"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"article-title":"Playing atari with deep reinforcement learning","year":"0","author":"mnih","key":"ref1"},{"key":"ref20","first-page":"3015","article-title":"Whitening for self-supervised representation learning","author":"ermolov","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref22","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"zbontar","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"article-title":"Data-efficient reinforcement learning with self-predictive representations","year":"2020","author":"schwarzer","key":"ref24"},{"key":"ref23","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume":"29","author":"sohn","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref25","article-title":"Recurrent world models facilitate policy evolution","volume":"31","author":"ha","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956553.pdf?arnumber=9956553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T15:05:36Z","timestamp":1671462336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956553","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}