{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:21:49Z","timestamp":1780053709286,"version":"3.54.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CPS-1739964,IIS-1724157,NRI-1925082"],"award-info":[{"award-number":["CPS-1739964,IIS-1724157,NRI-1925082"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160583","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"9224-9230","source":"Crossref","is-referenced-by-count":42,"title":["Benchmarking Reinforcement Learning Techniques for Autonomous Navigation"],"prefix":"10.1109","author":[{"given":"Zifan","family":"Xu","sequence":"first","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuesu","family":"Xiao","sequence":"additional","affiliation":[{"name":"George Mason University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anirudh","family":"Nair","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref34","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74690-4_71"},{"key":"ref14","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"0","journal-title":"AAAI Fall Symp"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965078"},{"key":"ref30","article-title":"Stanford Artificial Intelligence Laboratory","year":"0","journal-title":"The Robot Operating System"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref33","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref10","article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","author":"justesen","year":"2018","journal-title":"arXiv Learning"},{"key":"ref32","author":"fujimoto","year":"2018","journal-title":"Addressing Function Approximation Error in Actor-Critic Methods"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1993.291936"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref16","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561311"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3002217"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968004"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3100940"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104132"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561647"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848048"},{"key":"ref8","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2019","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6160783"},{"key":"ref9","article-title":"Leveraging procedural generation to benchmark reinforcement learning","author":"cobbe","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-022-10039-8"},{"key":"ref3","article-title":"Autonomous ground navigation in highly constrained spaces: Lessons learned from the barn challenge at icra 2022","author":"xiao","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref6","author":"thomas","year":"2022","journal-title":"Safe reinforcement learning by imagining the near future"},{"key":"ref5","article-title":"Lyapunov-based safe policy optimization for continuous control","author":"chow","year":"2019","journal-title":"CoRR"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160583.pdf?arnumber=10160583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:38:18Z","timestamp":1690220298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160583","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}