{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:46:22Z","timestamp":1774716382838,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/itsc.2018.8569400","type":"proceedings-article","created":{"date-parts":[[2018,12,13]],"date-time":"2018-12-13T01:21:46Z","timestamp":1544664106000},"page":"2377-2382","source":"Crossref","is-referenced-by-count":53,"title":["POMDP and Hierarchical Options MDP with Continuous Actions for Autonomous Driving at Intersections"],"prefix":"10.1109","author":[{"given":"Zhiqian","family":"Qiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katharina","family":"Muelling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Dolan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Praveen","family":"Palanisamy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Priyantha","family":"Mudalige","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref11","author":"egorov","year":"2015","journal-title":"Deep reinforcement learning with pomdps"},{"key":"ref12","volume":"abs 1507 6527","author":"hausknecht","year":"2015","journal-title":"Deep recurrent q-learning for partially observable mdps"},{"key":"ref13","author":"foerster","year":"2016","journal-title":"Learning to communicate to solve riddles with deep distributed recurrent q-networks"},{"key":"ref14","author":"zhu","year":"2018","journal-title":"On improving deep reinforcement learning for pomdps"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992700"},{"key":"ref16","first-page":"118","article-title":"The maxq method for hierarchical reinforcement learning","volume":"98","author":"dietterich","year":"1998","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390211"},{"key":"ref18","first-page":"213","article-title":"R-max-a general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995935"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1068\/p050437"},{"key":"ref6","author":"isele","year":"2017","journal-title":"Transferring autonomous driving knowledge on simulated and real intersections"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206316"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/1025349"},{"key":"ref7","author":"isele","year":"2017","journal-title":"Navigating Intersections with Autonomous Vehicles using Deep Reinforcement Learning"},{"key":"ref2","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.28.1.1"},{"key":"ref20","author":"steckelmacher","year":"2017","journal-title":"Reinforcement learning in pomdps with memoryless options and option-observation initiation sets"},{"key":"ref22","first-page":"220","article-title":"Hierarchical solution of markov decision processes using macro-actions","author":"hauskrecht","year":"1998","journal-title":"Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref21","first-page":"823","article-title":"Bounded finite state controllers","author":"poupart","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIT.2014.7019528"},{"key":"ref23","article-title":"Recent development and applications of sumo-simulation of urban mobility","volume":"5","author":"krajzewicz","year":"2012","journal-title":"International Journal on Advances in Systems and Measurements"},{"key":"ref25","year":"2005","journal-title":"NGSIM homepage FHWA"}],"event":{"name":"2018 21st International Conference on Intelligent Transportation Systems (ITSC)","location":"Maui, HI","start":{"date-parts":[[2018,11,4]]},"end":{"date-parts":[[2018,11,7]]}},"container-title":["2018 21st International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8543039\/8569013\/08569400.pdf?arnumber=8569400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:33:05Z","timestamp":1598229185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8569400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/itsc.2018.8569400","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}