{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T05:05:21Z","timestamp":1782623121564,"version":"3.54.5"},"reference-count":31,"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\/iros40897.2019.8967945","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"3534-3541","source":"Crossref","is-referenced-by-count":12,"title":["Comparison of Deep Reinforcement Learning Policies to Formal Methods for Moving Obstacle Avoidance"],"prefix":"10.1109","author":[{"given":"Arpit","family":"Garg","sequence":"first","affiliation":[{"name":"University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao-Tien Lewis","family":"Chiang","sequence":"additional","affiliation":[{"name":"University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satomi","family":"Sugaya","sequence":"additional","affiliation":[{"name":"University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aleksandra","family":"Faust","sequence":"additional","affiliation":[{"name":"Google AI,Mountain View,CA,USA,94043"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lydia","family":"Tapia","sequence":"additional","affiliation":[{"name":"University of New Mexico, MSC01 11301 University of New Mexico,Department of Computer Science,Albuquerque,NM,USA,87131"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891491"},{"key":"ref13","first-page":"3052","article-title":"Motion planning among dynamic, decision-making agents with deep reinforcement learning","author":"everett","year":"2018","journal-title":"Proc IEEE Int Conf on Intel Robot Sys (IROS)"},{"key":"ref14","first-page":"1805","article-title":"Simple random search of static linear policies is competitive for reinforcement learning","author":"mania","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16595-0_5"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf on Machine Learning (ICML)"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.1109\/TRO.2017.2705034","article-title":"Hybrid dynamic moving obstacle avoidance using a stochastic reachable set-based potential field","author":"malone","year":"2017","journal-title":"IEEE Trans Robot"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487169"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref28","article-title":"Sbeed: Convergent reinforcement learning with nonlinear function approximation","author":"dai","year":"2017","journal-title":"arXiv preprint arXiv 1712 10285"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1987.42"},{"key":"ref27","volume":"5","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1007\/978-3-319-27702-8_40","article-title":"Spencer: A socially aware service robot for passenger guidance and help in busy airports","author":"triebel","year":"2016","journal-title":"Field and Service Robotics"},{"key":"ref6","first-page":"1","article-title":"Safety, challenges, and performance of motion planners in dynamic environments","author":"chiang","year":"2017","journal-title":"Int Symposium on Robotics Research (ISRR)"},{"key":"ref29","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf on Machine Learning (ICML)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/62212.62257"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700706"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281806"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-009-9383-1"},{"key":"ref9","article-title":"Qtopt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"arXiv preprint arXiv 1806 10293"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530514"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.03.027"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.851439"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910387173"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2562059.2562127"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"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\/08967945.pdf?arnumber=8967945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:39:45Z","timestamp":1753731585000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967945","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}