{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T09:05:42Z","timestamp":1759482342719,"version":"3.44.0"},"reference-count":45,"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\/iros40897.2019.8967737","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"5086-5093","source":"Crossref","is-referenced-by-count":2,"title":["A-EXP4: Online Social Policy Learning for Adaptive Robot-Pedestrian Interaction"],"prefix":"10.1109","author":[{"given":"Pengju","family":"Jin","sequence":"first","affiliation":[{"name":"Authors are affiliated with the Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,PA 15213"}]},{"given":"Eshed","family":"Ohn-Bar","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems."}]},{"given":"Kris","family":"Kitani","sequence":"additional","affiliation":[{"name":"Authors are affiliated with the Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,PA 15213"}]},{"given":"Chieko","family":"Asakawa","sequence":"additional","affiliation":[{"name":"Authors are affiliated with the Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,PA 15213"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2935334.2935361"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907245"},{"journal-title":"An unsupervised approach to modelling visual data","year":"0","author":"steinberg","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1214\/06-BA104"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1984.4767596"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2571067"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2982142.2982178"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3132525.3132535"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2016.7451806"},{"journal-title":"Pedsim Pedestrian Crowd Simulator","year":"0","author":"gloor","key":"ref34"},{"key":"ref10","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM.2018.8444593"},{"key":"ref11","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CoASE.2015.7294140"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9132-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref15","first-page":"849","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2009","journal-title":"Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2012.6400808"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v27i1.8542","article-title":"Bayesian nonparametric multi-optima policy search in reinforcement learning","author":"bruno","year":"2013","journal-title":"AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759036"},{"key":"ref28","article-title":"Contextual bandit algorithms with supervised learning guarantees","author":"beygelzimer","year":"2011","journal-title":"AISTATS"},{"key":"ref4","article-title":"Efficient algorithms for adversarial contextual learning","author":"syrgkanis","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref27","article-title":"Tighter bounds for multi-armed bandits with expert advice","author":"mcmahan","year":"2009","journal-title":"COLT"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"},{"key":"ref29","first-page":"3168","article-title":"Explore no more: Improved high-probability regret bounds for non-stochastic bandits","author":"neu","year":"2015","journal-title":"Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref8","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.926867"},{"key":"ref9","article-title":"Personalized dynamics models for adaptive assistive navigation systems","author":"ohn-bar","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-295X.96.3.506"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354147"},{"key":"ref45","article-title":"Bootstrapped Thompson sampling and deep exploration","author":"osband","year":"2015","journal-title":"arXiv preprint arXiv 1507 00300"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.493"},{"key":"ref21","article-title":"Activity forecasting","author":"kitani","year":"2012","journal-title":"European Conference on Computer Vision"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460994"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2016.2553126"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MSMC.2015.2501167"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5772\/54933"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917743319"},{"key":"ref43","article-title":"How context and user behavior affect indoor navigation assistance for blind people","author":"guerreiro","year":"2018","journal-title":"W4A"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2011.6181523"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","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\/08967737.pdf?arnumber=8967737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:08:16Z","timestamp":1757095696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967737","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}