{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T03:04:50Z","timestamp":1770347090130,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968173","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"6822-6827","source":"Crossref","is-referenced-by-count":16,"title":["Learning Q-network for Active Information Acquisition"],"prefix":"10.1109","author":[{"given":"Heejin","family":"Jeong","sequence":"first","affiliation":[{"name":"University of Pennsylvania,department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brent","family":"Schlotfeldt","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hamed","family":"Hassani","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manfred","family":"Morari","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel D.","family":"Lee","sequence":"additional","affiliation":[{"name":"Cornell University,department of Electrical and Computer Engineering,Ithaca,NY,USA,14850"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George J.","family":"Pappas","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908099853"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2674"},{"key":"ref10","author":"sutton","year":"1988","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref12","first-page":"1","article-title":"Reinforcement learning for humanoid robotics","author":"peters","year":"2003","journal-title":"Proc IEEE-RAS Int Conf Humanoid Robots (Humanoids)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759250"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2004.17"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570193"},{"key":"ref16","article-title":"Controlled Recognition Bounds for Visual Learning and Exploration","author":"karasev","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631173"},{"key":"ref18","article-title":"Deep tracking: Seeing beyond seeing using recurrent neural networks","author":"ondruska","year":"2016","journal-title":"Proc of the Thirtieth AAAI Conf on Artif Intell"},{"key":"ref19","article-title":"Online multi-target tracking using recurrent neural networks","author":"milan","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.051"},{"key":"ref4","first-page":"529","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Science"},{"key":"ref27","first-page":"2775","article-title":"Bridging the gap between value and policy based reinforcement learning","author":"nachum","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Advances in Neural Information Processing Systems (NIPS) Deep Learning Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/362"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref5","article-title":"Deep reinforcement learning with double q-learning","author":"hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.3.441"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989112"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1115\/1.4027892"},{"key":"ref20","article-title":"End-to-end active object tracking via reinforcement learning","author":"luo","year":"2017","journal-title":"arXiv preprint arXiv 1705 10561"},{"key":"ref22","article-title":"Deep reinforcement learning for visual object tracking in videos","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1701 08241"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.531"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2794608"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.05.009"},{"key":"ref26","article-title":"Active information acquisition","author":"he","year":"2016","journal-title":"arXiv preprint arXiv 1602 0218"},{"key":"ref25","first-page":"4376","article-title":"Backprop kf: Learning discriminative deterministic state estimators","author":"haarnoja","year":"2016","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968173.pdf?arnumber=8968173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:08:19Z","timestamp":1757095699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968173","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}