{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:40:04Z","timestamp":1773772804321,"version":"3.50.1"},"reference-count":38,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636442","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T15:45:38Z","timestamp":1639669538000},"page":"4493-4500","source":"Crossref","is-referenced-by-count":12,"title":["KB-Tree: Learnable and Continuous Monte-Carlo Tree Search for Autonomous Driving Planning"],"prefix":"10.1109","author":[{"given":"Lanxin","family":"Lei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiming","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renjie","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingke","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"JianWei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liulong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyang","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-011-9258-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref31","article-title":"Bandit based monte-carlo planning","author":"kocsis","year":"2006","journal-title":"Machine Learning ECML 2006 17th European Conference on Machine Learning Berlin Germany September 18-22 2006 Proceedings"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"ref36","first-page":"66","article-title":"Learning by cheating","author":"chen","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref35","article-title":"Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst","author":"bansal","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6546"},{"key":"ref11","article-title":"Poly-hoot: Monte-carlo planning in continuous space mdps with non-asymptotic analysis","author":"mao","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3233\/ICG-2007-30403"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1142\/S1793005708001094"},{"key":"ref14","first-page":"525","article-title":"Boa: The bayesian optimization algorithm","volume":"1","author":"pelikan","year":"1999","journal-title":"Proceedings of the Genetic and Evolutionary Computation Conference GECCO-99"},{"key":"ref15","author":"bishop","year":"1994","journal-title":"Mixture density networks"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref17","article-title":"Mastering the game of go without human knowledge","author":"david","year":"2017","journal-title":"Nature"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref19","article-title":"Mastering atari, go, chess and shogi by planning with a learned model","author":"schrittwieser","year":"2019"},{"key":"ref28","article-title":"Bayesian optimized monte carlo planning","author":"mern","year":"2020"},{"key":"ref4","article-title":"A survey of deep network solutions for learning control in robotics: From reinforcement to imitation","author":"tai","year":"2016"},{"key":"ref27","article-title":"Bayesian optimisation for solving continuous state-action-observation pomdps","author":"morere","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.018"},{"key":"ref6","first-page":"2937","article-title":"Deep reinforcement learning in continuous action spaces: a case study in the game of simulated curling","author":"lee","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref29","article-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"laurence","year":"1995","journal-title":"Technometrics"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref8","article-title":"Policy gradient search: Online planning and expert iteration without search trees","author":"anthony","year":"2019"},{"key":"ref7","first-page":"690","article-title":"Monte carlo tree search in continuous action spaces with execution uncertainty","author":"yee","year":"2016","journal-title":"IJCAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.08.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5885"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS-C51114.2020.00045"},{"key":"ref20","article-title":"X-armed bandits","volume":"12","author":"bubeck","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","article-title":"Online optimization in x-armed bandits","author":"bubeck","year":"2008","journal-title":"The Twenty-Second Annual Conference on Neural Information Processing Systems"},{"key":"ref21","article-title":"Optimistic optimization of deterministic functions without the knowledge of its smoothness","author":"munos","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v22i1.13507","article-title":"Bandit-based planning and learning in continuous-action markov decision processes","volume":"22","author":"weinstein","year":"2012","journal-title":"Proceedings of the International Conference on Automated Planning and Scheduling"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v21i1.13484","article-title":"Sample-based planning for continuous action markov decision processes","volume":"21","author":"mansley","year":"2011","journal-title":"Proceedings of the International Conference on Automated Planning and Scheduling"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013815314823"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6546"}],"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\/09636442.pdf?arnumber=9636442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T17:39:45Z","timestamp":1674063585000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636442","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}