{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:25:02Z","timestamp":1781619902490,"version":"3.54.5"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100013020","name":"Compute Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013020","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636140","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"5619-5626","source":"Crossref","is-referenced-by-count":73,"title":["Memory-based Deep Reinforcement Learning for POMDPs"],"prefix":"10.1109","author":[{"given":"Lingheng","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rob","family":"Gorbet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dana","family":"Kulic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1287\/moor.22.1.222"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref30","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref37","first-page":"255","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proceedings of the Fourth Connectionist Models Summer School"},{"key":"ref36","volume":"1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref10","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref12","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018"},{"key":"ref13","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref14","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref15","first-page":"3x","article-title":"A survey of pomdp solution techniques","volume":"2","author":"murphy","year":"2000","journal-title":"Environment"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979695"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.04.001"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5220\/0007520305640572"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487174"},{"key":"ref4","article-title":"Towards vision-based deep reinforcement learning for robotic motion control","author":"zhang","year":"2015"},{"key":"ref27","article-title":"Memory-based control with recurrent neural networks","author":"heess","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803357"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref8","article-title":"Learning to engage with interactive systems: A field study on deep reinforcement learning in a public museum","volume":"10","author":"meng","year":"2020","journal-title":"Human Robot Interaction"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10827","article-title":"Playing fps games with deep reinforcement learning","volume":"31","author":"lample","year":"2017","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030143"},{"key":"ref22","article-title":"Artificial intelligence: a modern approach","author":"russell","year":"2002"},{"key":"ref21","first-page":"422431","article-title":"Reinforcement learning of active vision for manipulating objects under occlusions","author":"cheng","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref24","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2018.8581309"},{"key":"ref25","article-title":"On improving deep reinforcement learning for pomdps","author":"zhu","year":"2017"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636140.pdf?arnumber=9636140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T22:37:54Z","timestamp":1674081474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636140","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}