{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:29:45Z","timestamp":1762522185349,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.23919\/acc.2018.8431911","type":"proceedings-article","created":{"date-parts":[[2018,8,17]],"date-time":"2018-08-17T20:16:10Z","timestamp":1534536970000},"page":"762-769","source":"Crossref","is-referenced-by-count":9,"title":["Human-in-the-Loop Synthesis for Partially Observable Markov Decision Processes"],"prefix":"10.23919","author":[{"given":"Steven","family":"Carr","sequence":"first","affiliation":[]},{"given":"Nils","family":"Jansen","sequence":"additional","affiliation":[]},{"given":"Ralf","family":"Wimmer","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Ufuk","family":"Topcu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1987.10478458"},{"key":"ref38","first-page":"520","article-title":"Heuristic search value iteration for POMDPs","author":"smith","year":"2004","journal-title":"UAI"},{"journal-title":"Introduction to Stochastic Dynamic Programming","year":"1983","author":"ross","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2011.6005272"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794797"},{"key":"ref30","first-page":"1025","article-title":"Point-based value iteration: An anytime algorithm for POMDPs","volume":"3","author":"pineau","year":"2003","journal-title":"IJCAI"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570193"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/bdm.413"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"ref34","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"AISTATS"},{"journal-title":"Deep reinforcement learning from human preferences","year":"2017","author":"christiano","key":"ref10"},{"journal-title":"Probabilistic Robotics","year":"2005","author":"thrun","key":"ref40"},{"journal-title":"Cognitive models of memory","year":"1997","author":"conway","key":"ref11"},{"key":"ref12","first-page":"592","article-title":"A Storm is coming: A modern probabilistic model checker","author":"dehnert","year":"2017","journal-title":"CAV"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2502"},{"key":"ref14","first-page":"335","article-title":"Inverse optimal control with linearly-solvable MDPs","author":"dvijotham","year":"2010","journal-title":"ICML"},{"journal-title":"Dynamic Programming and Markov Processes","year":"1960","author":"howard","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963224"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.scico.2014.02.001"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1982.12425"},{"journal-title":"Permissive finite-state controllers of pomdps using parameter synthesis","year":"2017","author":"junges","key":"ref19"},{"key":"ref28","first-page":"417","article-title":"Solving POMDPs by searching the space of finite policies","author":"meuleau","year":"1999","journal-title":"UAI"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363691"},{"key":"ref27","first-page":"541","article-title":"On the undecidability of probabilistic planning and infinite-horizon partially observable Markov decision problems","author":"madani","year":"1999","journal-title":"AAAI"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref6","first-page":"1023","article-title":"Acting optimally in partially observable stochastic domains","volume":"94","author":"cassandra","year":"1994","journal-title":"AAAI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11241-017-9269-4"},{"key":"ref5","first-page":"362","article-title":"Learning policies for partially observable environments: Scaling up","author":"cassandra","year":"2016","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2016.01.007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-009-9103-z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21236\/ADA458138"},{"key":"ref1","first-page":"65","article-title":"Counterexample generation for discrete-time Markov models: An introductory survey","author":"\u00e1brah\u00e1m","year":"2014","journal-title":"SFM"},{"key":"ref46","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426524"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916688949"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2933575.2934574"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/4236.914647"},{"key":"ref24","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref41","first-page":"12:1","article-title":"On the computational complexity of stochastic controller optimization in POMDPs","volume":"4","author":"nikos","year":"2012","journal-title":"ACM Trans on Computation Theory"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2006.05.003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263971"},{"key":"ref26","first-page":"238","article-title":"Memoryless policies: Theoretical limitations and practical results","author":"littman","year":"1994","journal-title":"SAB"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2168\/LMCS-11(1:15)2015"},{"key":"ref25","first-page":"585","article-title":"Prism 4.0: Verification of probabilistic real-time systems","author":"kwiatkowska","year":"2011","journal-title":"CAV"}],"event":{"name":"2018 Annual American Control Conference (ACC)","start":{"date-parts":[[2018,6,27]]},"location":"Milwaukee, WI","end":{"date-parts":[[2018,6,29]]}},"container-title":["2018 Annual American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8410068\/8430677\/08431911.pdf?arnumber=8431911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T02:28:11Z","timestamp":1598236091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8431911\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.23919\/acc.2018.8431911","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}