{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:35:57Z","timestamp":1740177357120,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"OP RDE Funded Project Research Center for Informatics","award":["CZ.02.1.01\/0.0.\/0.0.\/16_019\/0000765"],"award-info":[{"award-number":["CZ.02.1.01\/0.0.\/0.0.\/16_019\/0000765"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tcds.2021.3050723","type":"journal-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T04:17:10Z","timestamp":1610511430000},"page":"485-496","source":"Crossref","is-referenced-by-count":4,"title":["Augmented Memory Replay in Reinforcement Learning With Continuous Control"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6302-4515","authenticated-orcid":false,"given":"Mirza","family":"Ramicic","sequence":"first","affiliation":[{"name":"Artificial Intelligence Center, Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4880-4521","authenticated-orcid":false,"given":"Andrea","family":"Bonarini","sequence":"additional","affiliation":[{"name":"Dipartimento di Elettronica, Informazione e Bioingegneria, Artificial Intelligence and Robotics Lab, Politecnico di Milano, Milan, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2017","author":"dai","journal-title":"Boosting the actor with dual critic","key":"ref39"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/IROS.2012.6386025"},{"year":"2015","author":"hausknecht","journal-title":"Deep Reinforcement Learning in Parameterized Action Space","key":"ref33"},{"year":"2015","author":"lillicrap","journal-title":"Continuous control with deep reinforcement learning","key":"ref32"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1007\/BF00992698"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1007\/978-3-642-32375-1_2"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.15607\/RSS.2011.VII.010"},{"year":"2016","author":"wang","journal-title":"Sample efficient actor-critic with experience replay","key":"ref36"},{"key":"ref35","first-page":"5400","article-title":"Evolved policy gradients","author":"houthooft","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref34","first-page":"36","article-title":"Half field offense: An environment for multiagent learning and ad hoc teamwork","author":"hausknecht","year":"2016","journal-title":"Proc AAMAS Adapt Learn Agents (ALA) Workshop"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1016\/j.neunet.2005.08.010"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1038\/nn1202"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1016\/j.tics.2016.05.004"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/S1364-6613(99)01294-2"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/2.33"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/TSMC.1983.6313077"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1002\/hipo.450040605"},{"year":"1996","author":"o\u2019reilly","article-title":"The leabra model of neural interactions and learning in the neocortex","key":"ref21"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.7551\/mitpress\/2014.001.0001"},{"key":"ref23","first-page":"73","article-title":"A hippocampal model of recognition memory","author":"o\u2019reilly","year":"1998","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1037\/0033-295X.110.4.611"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.3758\/CABN.1.1.66"},{"year":"2016","author":"brockman","journal-title":"OpenAI Gym","key":"ref50"},{"year":"2019","author":"raffin","journal-title":"Stable baselines3","key":"ref51"},{"key":"ref57","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"year":"2017","author":"schulman","journal-title":"Proximal policy optimization algorithms","key":"ref56"},{"doi-asserted-by":"publisher","key":"ref55","DOI":"10.1016\/j.cogsys.2019.01.006"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1109\/ICIVC.2017.7984718"},{"year":"2015","author":"schulman","journal-title":"High-dimensional continuous control using generalized advantage estimation","key":"ref53"},{"year":"2020","author":"raffin","journal-title":"Rl baselines zoo","key":"ref52"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1007\/978-1-4684-6775-8_5"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/BF03337774"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1371\/journal.pone.0187463"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1016\/j.neuron.2010.01.034"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1038\/s41593-019-0464-6"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1016\/j.cobeha.2020.02.008"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1016\/j.cortex.2015.06.007"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1016\/j.cortex.2016.06.011"},{"year":"1993","author":"lin","article-title":"Reinforcement learning for robots using neural networks","key":"ref17"},{"year":"2013","author":"mnih","journal-title":"Playing atari with deep reinforcement learning","key":"ref18"},{"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"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1038\/35039559"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1146\/annurev.neuro.20.1.157"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1126\/science.1062856"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1037\/0033-295X.102.3.419"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1038\/nature04286"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1016\/j.conb.2007.11.007"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.neunet.2019.10.011","article-title":"A complementary learning systems approach to temporal difference learning","volume":"122","author":"mareschal","year":"2020","journal-title":"Neural Netw"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1038\/nrn2762"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1145\/122344.122377"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1038\/s41593-018-0232-z"},{"key":"ref48","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1007\/s00422-020-00817-x"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1007\/978-3-540-74913-4_30"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1109\/TAMD.2010.2051031"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1109\/TCDS.2019.2896306"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1016\/j.cogsys.2018.04.014"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/9793367\/09319729.pdf?arnumber=9319729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:44:09Z","timestamp":1656362649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9319729\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":57,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2021.3050723","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}