{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T13:49:57Z","timestamp":1778075397955,"version":"3.51.4"},"reference-count":39,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160876","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"9428-9434","source":"Crossref","is-referenced-by-count":20,"title":["Improving robot navigation in crowded environments using intrinsic rewards"],"prefix":"10.1109","author":[{"given":"Diego","family":"Martinez-Baselga","sequence":"first","affiliation":[{"name":"Aragon Institute of Engineering Research (I3A), Universidad de Zaragoza,Robotics, Perception and Real Time Group,Zaragoza,Spain,50018"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Riazuelo","sequence":"additional","affiliation":[{"name":"Aragon Institute of Engineering Research (I3A), Universidad de Zaragoza,Robotics, Perception and Real Time Group,Zaragoza,Spain,50018"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Montano","sequence":"additional","affiliation":[{"name":"Aragon Institute of Engineering Research (I3A), Universidad de Zaragoza,Robotics, Perception and Real Time Group,Zaragoza,Spain,50018"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SII46433.2020.9025987"},{"key":"ref35","article-title":"Never give up: Learning directed exploration strategies","author":"badia","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560951"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460968"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2936167"},{"key":"ref36","first-page":"9443","article-title":"State entropy maximization with random encoders for efficient exploration","author":"seo","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref31","first-page":"1","article-title":"Exploration by random network distillation","author":"burda","year":"2019","journal-title":"the Seventh International Conference on Learning Representations"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5654369"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11467-017-0689-3"},{"key":"ref32","article-title":"Noisy networks for exploration","author":"fortunato","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2004.838026"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref39","first-page":"7977","article-title":"Dropout acts as auxiliary exploration","volume":"13","author":"sung","year":"2018","journal-title":"International Journal of Applied Engineering Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561462"},{"key":"ref38","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972868"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340705"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460504"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03191-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050338"},{"key":"ref22","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref28","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/09540099108946587"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-19457-3_1","article-title":"Reciprocal n-body collision avoidance","author":"berg","year":"2011","journal-title":"Robotics Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2003.12.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918775520"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700706"}],"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\/10160876.pdf?arnumber=10160876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:30:03Z","timestamp":1690219803000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160876\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160876","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}