{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:15:03Z","timestamp":1729631703090,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197297","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"8490-8496","source":"Crossref","is-referenced-by-count":2,"title":["Deep Imitative Reinforcement Learning for Temporal Logic Robot Motion Planning with Noisy Semantic Observations"],"prefix":"10.1109","author":[{"given":"Qitong","family":"Gao","sequence":"first","affiliation":[]},{"given":"Miroslav","family":"Pajic","sequence":"additional","affiliation":[]},{"given":"Michael M.","family":"Zavlanos","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511813603"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729330"},{"key":"ref33","article-title":"Sample-efficient reinforcement learning through transfer and architectural priors","author":"spector","year":"2018","journal-title":"arXiv preprint arXiv 1801 02929"},{"key":"ref32","article-title":"Sample-efficient deep reinforcement learning via episodic backward update","author":"lee","year":"2018","journal-title":"arXiv preprint arXiv 1805 12375"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.064"},{"key":"ref37","article-title":"Cooperative motion and task planning under temporal tasks","author":"guo","year":"2014","journal-title":"Ph D Dissertation"},{"key":"ref36","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50763-7"},{"journal-title":"Principles of Model Checking","year":"2008","author":"baier","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2799561"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref40"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1145\/3302509.3311053","article-title":"Reduced variance deep reinforcement learning with temporal logic specifications","author":"gao","year":"2019","journal-title":"10th ACM\/IEEE International Conference on Cyber-Physical Systems (with CPS-IoT Week 2019)"},{"journal-title":"Probabilistic Robotics","year":"2005","author":"thrun","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139019"},{"key":"ref14","first-page":"233","article-title":"Temporal logic motion planning using pomdps with parity objectives: case study paper","author":"svore?ov\u00e1","year":"2015","journal-title":"Proceedings of the 18th International Conference on Hybrid Systems Computation and Control"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224648"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-29363-9_27"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224727"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912456319"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363984"},{"key":"ref28","article-title":"Modeling and learning of complex motor tasks: A case study with robot table tennis","author":"muelling","year":"2013","journal-title":"Ph D Dissertation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3055004.3055027"},{"key":"ref27","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref3","first-page":"7","article-title":"Sampling-based optimal control synthesis for multi-robot systems under global temporal tasks","volume":"pp","author":"kantaros","year":"2018","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref6","article-title":"STyLuS?: A temporal logic optimal control synthesis algorithm for large-scale multi-robot systems","author":"kantaros","year":"2019","journal-title":"arXiv preprint arXiv 1809 08345"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS.2018.00024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2298143"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913519000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914546174"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6161122"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref20","article-title":"Supervisor synthesis of pomdp based on automata learning","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1703 08581"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.039"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581505"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039527"},{"key":"ref41","article-title":"Learning from delayed rewards","author":"watkins","year":"1989","journal-title":"Ph D Dissertation"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354078"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11757","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799279"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197297.pdf?arnumber=9197297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T14:02:49Z","timestamp":1668780169000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197297","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}