{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:08:55Z","timestamp":1780765735483,"version":"3.54.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196739","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"10688-10694","source":"Crossref","is-referenced-by-count":70,"title":["Discrete Deep Reinforcement Learning for Mapless Navigation"],"prefix":"10.1109","author":[{"given":"Enrico","family":"Marchesini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Farinelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-012-0072-5"},{"key":"ref32","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref31","article-title":"Taming the Noise in Reinforcement Learning via Soft Updates","author":"fox","year":"2015","journal-title":"AUAI"},{"key":"ref30","article-title":"Noisy Networks for Exploration","author":"fortunato","year":"2017","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref10","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref11","article-title":"Prioritized Experience Replay","author":"schaul","year":"2016","journal-title":"ICLRE"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759428"},{"key":"ref13","article-title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","author":"bellemare","year":"2012","journal-title":"JAIR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref15","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref17","article-title":"The Malmo Platform for Artificial Intelligence Experimentation","author":"johnson","year":"2016","journal-title":"IJCAI"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11215","article-title":"VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem","author":"clark","year":"2017","journal-title":"AAAI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref28","article-title":"Unity: A General Platform for Intelligent Agents","author":"juliani","year":"2018","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00080"},{"key":"ref27","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref3","article-title":"Towards Cognitive Exploration through Deep Reinforcement Learning for Mobile Robots","author":"tai","year":"2016","journal-title":"CoRR"},{"key":"ref6","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(96)00006-8"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref8","article-title":"Genetic deep reinforcement learning for mapless navigation","author":"marchesini","year":"2020","journal-title":"AAMAS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep Reinforcement Learning with Double Q-learning","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref1","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013","journal-title":"NIPS"},{"key":"ref20","article-title":"Off-road Obstacle Avoidance Through End-to-end Learning","author":"lecun","year":"2005","journal-title":"NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461203"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2012.2185849"},{"key":"ref26","article-title":"Multi-Batch Experience Replay for Fast Convergence of Continuous Action Control","author":"han","year":"2017","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196739.pdf?arnumber=9196739","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T14:02:14Z","timestamp":1668780134000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196739\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196739","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}