{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T23:06:23Z","timestamp":1769727983341,"version":"3.49.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8793613","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"9638-9644","source":"Crossref","is-referenced-by-count":11,"title":["Adaptive Genomic Evolution of Neural Network Topologies (AGENT) for State-to-Action Mapping in Autonomous Agents"],"prefix":"10.1109","author":[{"given":"Amir","family":"Behjat","sequence":"first","affiliation":[]},{"given":"Sharat","family":"Chidambaran","sequence":"additional","affiliation":[]},{"given":"Souma","family":"Chowdhury","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.04.005"},{"key":"ref32","article-title":"Advances in Experience Replay","author":"wan","year":"2018","journal-title":"arXiv preprint arXiv 1805 05536"},{"key":"ref31","article-title":"The effects of memory replay in reinforcement learning","author":"liu","year":"2017","journal-title":"arXiv preprint arXiv 1710 06574"},{"key":"ref30","article-title":"Actor-critic versus direct policy search: a comparison based on sample complexity","author":"de broissia","year":"2016","journal-title":"arXiv preprint arXiv 1606 09152"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-012-0851-z"},{"key":"ref35","author":"paul","year":"2017","journal-title":"A Bio-inspired Neural System for Energy Optimal Collision Avoidance by Unmanned Aerial Vehicles"},{"key":"ref34","article-title":"Translating paths into optimal trajectories for safe coordination of teams of dynamic robots","author":"tang","year":"2016","journal-title":"Robotics Science and Systems(RSS) Robotics Science and Systems (RSS) Workshop on On-line Decision-Making in Multi-robot Coordination"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2018.7511144"},{"key":"ref11","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv preprint arXiv 1703 04529"},{"key":"ref12","article-title":"Direct policy search and uncertain policy evaluation","author":"schmidhuber","year":"1998","journal-title":"AAAI Spring Symposium on Search Under Uncertain and Incomplete Information Stanford Univ"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2494596"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-58484-6_288"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1162\/106365602320169811","article-title":"Ef?cient reinforcement learning through evolving neural network topologies","author":"stanley","year":"2002","journal-title":"Proc of the Annual Conference on Genetic and Evolutionary Computation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/artl.2009.15.2.15202"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2330163.2330195"},{"key":"ref19","article-title":"Evolving robot gaits in hardware: the Hyper-NEAT generative encoding vs. parameter optimization","author":"yosinski","year":"2011","journal-title":"ECAL"},{"key":"ref28","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref4","first-page":"1","article-title":"Reinforcement learning for humanoid robotics","author":"peters","year":"2003","journal-title":"Proceedings of the Third IEEE-RAS International Conference on Humanoid Robots"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2307\/2033241"},{"key":"ref3","article-title":"Knightcap: a chess program that learns by combining td (lambda) with game-tree search","author":"baxter","year":"1999","journal-title":"arXiv preprint cs\/9905014"},{"key":"ref6","article-title":"Backpropagation through the void: Optimizing control variates for black-box gradient estimation","author":"grathwohl","year":"2017","journal-title":"arXiv preprint arXiv 1711 03890"},{"key":"ref29","author":"moore","year":"1990","journal-title":"Efficient memory-based learning for robot control"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518 7540","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-017-1054-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02621-3_15"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-007-0002-4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2008.09.015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2013.01.022"},{"key":"ref22","article-title":"Deep neuroevolution: genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"such","year":"2017","journal-title":"arXiv preprint arXiv 1712 06567"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.03.012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2018-86104"},{"key":"ref23","article-title":"A comparative analysis of simplification and complexification in the evolution of neural network topologies","author":"james","year":"2004","journal-title":"Proc of Genetic and Evolutionary Computation Conference"},{"key":"ref26","year":"2001","journal-title":"Multi-Objective Optimization Using Evolutionary Algorithms"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2551748"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08793613.pdf?arnumber=8793613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:08:09Z","timestamp":1657854489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793613","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}