{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:38:38Z","timestamp":1783183118085,"version":"3.54.6"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561647","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"6086-6092","source":"Crossref","is-referenced-by-count":32,"title":["APPLR: Adaptive Planner Parameter Learning from Reinforcement"],"prefix":"10.1109","author":[{"given":"Zifan","family":"Xu","sequence":"first","affiliation":[{"name":"University of Texas at Austin,Department of Physics,Austin,Texas,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gauraang","family":"Dhamankar","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science,Austin,Texas,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anirudh","family":"Nair","sequence":"additional","affiliation":[{"name":"Mathematics, University of Texas at Austin,Austin,Texas,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuesu","family":"Xiao","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science,Austin,Texas,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Garrett","family":"Warnell","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science,Austin,Texas,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science,Austin,Texas,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zizhao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Electrical and Computer Engineering,Austin,Texas,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science,Austin,Texas,78712"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Lifelong navigation","author":"liu","year":"2020"},{"key":"ref11","article-title":"Agile robot navigation through hallucinated learning and sober deployment","author":"xiao","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.030"},{"key":"ref13","article-title":"Badgr: An autonomous self-supervised learning-based navigation system","author":"kahn","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794062"},{"key":"ref16","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018"},{"key":"ref17","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014"},{"key":"ref18","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8090935"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3002217"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"ref5","article-title":"Differentiable gaussian process motion planning","author":"bhardwaj","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref7","article-title":"Intentionnet: Integrating planning and deep learning for goal-directed autonomous navigation","author":"gao","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206510"},{"key":"ref1","article-title":"Ros navigation tuning guide","author":"zheng","year":"2017"},{"key":"ref9","article-title":"Toward agile maneuvers in highly constrained spaces: Learning from hallucination","author":"xiao","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/SSRR50563.2020.9292572","article-title":"Benchmarking metric ground navigation","author":"perille","year":"2020"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561647.pdf?arnumber=9561647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:47:27Z","timestamp":1673563647000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561647","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}