{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:52:34Z","timestamp":1782996754818,"version":"3.54.5"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"United States Air Force Research Laboratory (AFRL) and Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-18-C-0103"],"award-info":[{"award-number":["FA8750-18-C-0103"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","award":["2020R1A6A1A03040570"],"award-info":[{"award-number":["2020R1A6A1A03040570"]}],"id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1109\/tnnls.2021.3110281","type":"journal-article","created":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T20:16:04Z","timestamp":1632514564000},"page":"2045-2056","source":"Crossref","is-referenced-by-count":20,"title":["Deep Reinforcement Learning With Modulated Hebbian Plus Q-Network Architecture"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1154-8333","authenticated-orcid":false,"given":"Pawel","family":"Ladosz","sequence":"first","affiliation":[{"name":"Department of Computer Science, Loughborough University, Loughborough, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1176-866X","authenticated-orcid":false,"given":"Eseoghene","family":"Ben-Iwhiwhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Loughborough University, Loughborough, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffery","family":"Dick","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Loughborough University, Loughborough, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas","family":"Ketz","sequence":"additional","affiliation":[{"name":"Information and Systems Sciences Laboratory, HRL Laboratories, Malibu, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soheil","family":"Kolouri","sequence":"additional","affiliation":[{"name":"Information and Systems Sciences Laboratory, HRL Laboratories, Malibu, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0739-2468","authenticated-orcid":false,"given":"Jeffrey L.","family":"Krichmar","sequence":"additional","affiliation":[{"name":"Department of Cognitive Sciences and the Department of Computer Science, University of California at Irvine, Irvine, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9762-2882","authenticated-orcid":false,"given":"Praveen K.","family":"Pilly","sequence":"additional","affiliation":[{"name":"Information and Systems Sciences Laboratory, HRL Laboratories, Malibu, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9750-8358","authenticated-orcid":false,"given":"Andrea","family":"Soltoggio","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Loughborough University, Loughborough, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","volume-title":"arXiv:1312.5602","author":"Mnih","year":"2013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74690-4_71"},{"key":"ref3","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. AAAI Fall Symp.","author":"Hausknecht"},{"key":"ref4","article-title":"Memory-based control with recurrent neural networks","volume-title":"arXiv:1512.04455","author":"Heess","year":"2015"},{"key":"ref5","article-title":"Learning to navigate in complex environments","volume-title":"arXiv:1611.03673","author":"Mirowski","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/jigpal\/jzp049"},{"key":"ref7","article-title":"On improving deep reinforcement learning for POMDPs","volume-title":"arXiv:1804.06309","author":"Zhu","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2854283"},{"key":"ref9","article-title":"AMRL: Aggregated memory for reinforcement learning","volume-title":"Proc. ICLR","author":"Beck"},{"key":"ref10","article-title":"Low-pass recurrent neural networks\u2013a memory architecture for longer-term correlation discovery","volume-title":"arXiv:1805.04955","author":"Stepleton","year":"2018"},{"key":"ref11","article-title":"Neural map: Structured memory for deep reinforcement learning","volume-title":"Proc. ICLR","author":"Parisotto"},{"key":"ref12","first-page":"2790","article-title":"Control of memory, active perception, and action in minecraft","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Oh"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487174"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11606"},{"key":"ref15","article-title":"Temporal abstraction in reinforcement learning","author":"Precup","year":"2000"},{"key":"ref16","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Deisenroth"},{"key":"ref17","first-page":"2040","article-title":"Data-efficient reinforcement learning in continuous state-action Gaussian-POMDPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"McAllister"},{"key":"ref18","first-page":"2117","article-title":"Deep variational reinforcement learning for POMDPs","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Igl"},{"key":"ref19","volume-title":"The Organization of Behavior: A Neuropsychological Theory","author":"Hebb","year":"1949"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00419"},{"key":"ref21","first-page":"3559","article-title":"Differentiable plasticity: Training plastic neural networks with backpropagation","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Miconi"},{"key":"ref22","article-title":"Backpropamine: Training self-modifying neural networks with differentiable neuromodulated plasticity","volume-title":"arXiv:2002.10585","author":"Miconi","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhl152"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2013.00006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2013.6652572"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref27","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Munos"},{"key":"ref28","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/3061053.3061259"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.59.4498"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.1.100"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.06.005"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9766240\/09547670.pdf?arnumber=9547670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:33:05Z","timestamp":1705015985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9547670\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5]]},"references-count":33,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3110281","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5]]}}}