{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T19:26:25Z","timestamp":1762025185104,"version":"build-2065373602"},"reference-count":29,"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\/icra40945.2020.9197262","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"7477-7483","source":"Crossref","is-referenced-by-count":14,"title":["On Simple Reactive Neural Networks for Behaviour-Based Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ameya","family":"Pore","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerardo","family":"Aragon-Camarasa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref11","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018","journal-title":"arXiv preprint arXiv 1802 09085"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1016\/S0921-8890(05)80025-9"},{"key":"ref13","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"year":"2018","author":"levy","article-title":"Learning multi-level hierarchies with hindsight","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1177\/0278364913495721"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1177\/105971230501300101"},{"key":"ref17","article-title":"Meta learning shared hierarchies","author":"frans","year":"2017","journal-title":"arXiv preprint arXiv 1710 09767"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1145\/1553374.1553380"},{"key":"ref19","article-title":"Investigating human priors for playing video games","author":"dubey","year":"2018","journal-title":"arXiv preprint arXiv 1802 10363"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/LRA.2019.2928776"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICRA.2017.7989385"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1016\/j.swevo.2018.06.009"},{"key":"ref3","article-title":"Learning to walk via deep reinforcement learning","author":"haarnoja","year":"2018","journal-title":"arXiv preprint arXiv 1812 11467"},{"key":"ref6","article-title":"Vid2param: Online system identification from video for robotics applications","volume":"abs 1907 6422","author":"asenov","year":"2019","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.robot.2019.05.010","article-title":"Continuous perception for deformable objects understanding","volume":"118","author":"mart\u00ednez","year":"2019","journal-title":"Robotics and Autonomous Systems"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref8","article-title":"A dissection of overfitting and generalization in continuous reinforcement learning","author":"zhang","year":"2018","journal-title":"arXiv preprint arXiv 1806 07937"},{"key":"ref7","article-title":"Assessing generalization in deep reinforcement learning","author":"packer","year":"2018","journal-title":"arXiv preprint arXiv 1810 10053"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1016\/0004-3702(91)90053-M"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICRA.2018.8463162"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1016\/j.robot.2004.03.003"},{"key":"ref21","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"arXiv preprint arXiv 1604 07316"},{"key":"ref24","volume":"2","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11757","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref26","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv preprint arXiv 1506 02349"},{"key":"ref25","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","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\/09197262.pdf?arnumber=9197262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T13:57:35Z","timestamp":1668779855000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197262\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197262","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}