{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:23:40Z","timestamp":1730255020903,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412601","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"6786-6793","source":"Crossref","is-referenced-by-count":0,"title":["Trajectory representation learning for Multi-Task NMRDP planning"],"prefix":"10.1109","author":[{"given":"Firas","family":"Jarboui","sequence":"first","affiliation":[]},{"given":"Vianney","family":"Perchet","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"On improving deep reinforcement learning for pomdps","year":"2018","author":"zhu","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273624"},{"key":"ref31","first-page":"452","article-title":"Teaching multiple tasks to an rl agent using ltl","author":"icarte","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1676"},{"key":"ref10","first-page":"1087","article-title":"One-shot imitation learning","author":"duan","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"0","journal-title":"2015 AAAI Fall Symposium Series"},{"journal-title":"Defense of the Triplet Loss for Person Re-Identification","year":"2017","author":"hermans","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017616"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28231-2_35"},{"key":"ref16","first-page":"207","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"kilian","year":"2009","journal-title":"JMLR"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0196-6774(90)90003-W"},{"journal-title":"Efficient Estimation of Word Representations in Vector Space","year":"2013","author":"mikolov","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"ref4","first-page":"112","article-title":"Structured solution methods for non-markovian decision processes","author":"bacchus","year":"0","journal-title":"AAAI\/IAAI"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref3","first-page":"1160","article-title":"Rewarding behaviors","author":"bacchus","year":"0","journal-title":"Proceedings of the National Conference on Artificial Intelligence"},{"key":"ref6","article-title":"A survey of pomdp applications","volume":"1724","author":"cassandra","year":"0","journal-title":"Working Notes of AAAI 1998 Fall Symposium on Planning with Partially Observable Markov Decision Processes"},{"key":"ref29","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref5","first-page":"1475","article-title":"Reinforcement learning with long short-term memory","author":"bakker","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"1331","article-title":"Curious: Intrinsically motivated modular multi-goal reinforcement learning","author":"colas","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"journal-title":"A theoretical analysis of contrastive unsupervised representation learning","year":"2019","author":"arora","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.04.005"},{"key":"ref1","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Advances in neural information processing systems"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref20"},{"key":"ref22","first-page":"3x","article-title":"A survey of pomdp solution techniques","volume":"2","author":"murphy","year":"2000","journal-title":"Environment"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374611"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21236\/ADA164453"},{"journal-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables[J]","year":"2019","author":"rakelly","key":"ref25"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412601.pdf?arnumber=9412601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:49Z","timestamp":1652197249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412601","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}