{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:06:34Z","timestamp":1775912794495,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981250","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"9048-9053","source":"Crossref","is-referenced-by-count":6,"title":["BIMRL: Brain Inspired Meta Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Seyed Roozbeh","family":"Razavi Rohani","sequence":"first","affiliation":[{"name":"Sharif University of Technology,Department of Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saeed","family":"Hedayatian","sequence":"additional","affiliation":[{"name":"Sharif University of Technology,Department of Mathematical Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahdieh Soleymani","family":"Baghshah","sequence":"additional","affiliation":[{"name":"Sharif University of Technology,Department of Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Varibad: A very good method for bayes-adaptive deep rl via meta-learning","author":"Zintgraf","year":"2019","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Learning to reinforcement learn","author":"Wang","year":"2016","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"12991","article-title":"Exploration in approximate hyper-state space for meta reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Zintgraf"},{"key":"ref4","article-title":"H- mem: Harnessing synaptic plas-ticity with hebbian memory networks","author":"Limbacher","year":"2020","journal-title":"bioRxiv"},{"key":"ref5","first-page":"603","article-title":"Deep learning needs a prefrontal cortex","volume":"107","author":"Russin","year":"2020","journal-title":"Work Bridging AI Cogn Sci"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cobeha.2020.07.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-21407-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nrn.2017.74"},{"key":"ref9","article-title":"Recurrent independent mechanisms","author":"Goyal","year":"2019","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"6972","article-title":"Learning to combine top-down and bottom-up signals in recurrent neural networks with attention over modules","volume-title":"International Conference on Machine Learning","author":"Mittal"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-017-0180-8"},{"key":"ref13","article-title":"On the reliability and generalizability of brain-inspired reinforcement learning algorithms","author":"Kim","year":"2020","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005768"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.tins.2020.06.009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-018-0147-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2017.00438"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.03.044"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2019.00471"},{"key":"ref23","volume-title":"Minimalistic grid-world environment for openai gym","author":"Chevalier-Boisvert","year":"2018"},{"key":"ref24","article-title":"Bebold: Exploration beyond the boundary of explored regions","author":"Zhang","year":"2020","journal-title":"arXiv preprint"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981250.pdf?arnumber=9981250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:40:49Z","timestamp":1706758849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981250","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}