{"id":"https://openalex.org/W4312352946","doi":"https://doi.org/10.1109/iros47612.2022.9981250","title":"BIMRL: Brain Inspired Meta Reinforcement Learning","display_name":"BIMRL: Brain Inspired Meta Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312352946","doi":"https://doi.org/10.1109/iros47612.2022.9981250"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981250","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056956002","display_name":"Seyed Roozbeh Razavi Rohani","orcid":null},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Seyed Roozbeh Razavi Rohani","raw_affiliation_strings":["Sharif University of Technology,Department of Computer Engineering","Department of Computer Engineering, Sharif University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sharif University of Technology,Department of Computer Engineering","institution_ids":["https://openalex.org/I133529467"]},{"raw_affiliation_string":"Department of Computer Engineering, Sharif University of Technology","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000646515","display_name":"Saeed Hedayatian","orcid":null},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Saeed Hedayatian","raw_affiliation_strings":["Sharif University of Technology,Department of Mathematical Sciences","Department of Mathematical Sciences, Sharif University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sharif University of Technology,Department of Mathematical Sciences","institution_ids":["https://openalex.org/I133529467"]},{"raw_affiliation_string":"Department of Mathematical Sciences, Sharif University of Technology","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069082023","display_name":"Mahdieh Soleymani Baghshah","orcid":"https://orcid.org/0000-0002-1971-6231"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mahdieh Soleymani Baghshah","raw_affiliation_strings":["Sharif University of Technology,Department of Computer Engineering","Department of Computer Engineering, Sharif University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sharif University of Technology,Department of Computer Engineering","institution_ids":["https://openalex.org/I133529467"]},{"raw_affiliation_string":"Department of Computer Engineering, Sharif University of Technology","institution_ids":["https://openalex.org/I133529467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133529467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9048","last_page":"9053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.81755530834198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6407177448272705},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.630894124507904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4478427767753601},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4400234520435333},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20808586478233337},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12150055170059204},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05673801898956299}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.81755530834198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6407177448272705},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.630894124507904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478427767753601},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4400234520435333},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20808586478233337},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12150055170059204},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05673801898956299},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981250","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1980035368","https://openalex.org/W2606776585","https://openalex.org/W2640974754","https://openalex.org/W2733572936","https://openalex.org/W2736601468","https://openalex.org/W2949369413","https://openalex.org/W2950347959","https://openalex.org/W2950459925","https://openalex.org/W2953319434","https://openalex.org/W2963523627","https://openalex.org/W2980555752","https://openalex.org/W3007266467","https://openalex.org/W3039382151","https://openalex.org/W3040981400","https://openalex.org/W3045881384","https://openalex.org/W3090796177","https://openalex.org/W3113190209","https://openalex.org/W3127433878","https://openalex.org/W4214717370","https://openalex.org/W4300971732","https://openalex.org/W6729433768","https://openalex.org/W6741002519","https://openalex.org/W6768501859","https://openalex.org/W6769269530","https://openalex.org/W6780220573","https://openalex.org/W6780366824","https://openalex.org/W6780527974","https://openalex.org/W6784051664","https://openalex.org/W6787998924"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W3130669838","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"Sample":[0],"efficiency":[1],"has":[2],"been":[3],"a":[4,51,57,72,83],"key":[5],"issue":[6],"in":[7,46,99,115],"reinforcement":[8],"learning":[9],"(RL).":[10],"An":[11],"efficient":[12],"agent":[13],"must":[14],"be":[15],"able":[16],"to":[17,22,25,68,81],"leverage":[18],"its":[19],"prior":[20],"experiences":[21],"quickly":[23,66],"adapt":[24,67],"similar,":[26],"but":[27],"new":[28,69],"tasks":[29,70],"and":[30,38,102,110],"situations.":[31],"Meta-RL":[32],"is":[33,95,103],"one":[34],"attempt":[35],"at":[36],"formalizing":[37],"ad-dressing":[39],"this":[40,78],"issue.":[41],"Inspired":[42],"by":[43,97,127],"recent":[44],"progress":[45],"meta-RL,":[47],"we":[48],"introduce":[49],"BIMRL,":[50],"novel":[52,58,84],"multi-layer":[53],"architecture":[54,94],"along":[55],"with":[56,105,129],"brain-inspired":[59],"memory":[60,79],"module":[61,80],"that":[62,87],"will":[63,88],"help":[64],"agents":[65],"within":[71],"few":[73],"episodes.":[74],"We":[75,118],"also":[76],"utilize":[77],"design":[82],"intrinsic":[85],"reward":[86],"guide":[89],"the":[90,106,116,121,132],"agent's":[91],"exploration.":[92],"Our":[93],"inspired":[96],"findings":[98],"cognitive":[100],"neuroscience":[101],"compatible":[104],"knowledge":[107],"on":[108,138],"connectivity":[109],"functionality":[111],"of":[112,123,134],"different":[113],"regions":[114],"brain.":[117],"empirically":[119],"validate":[120],"effectiveness":[122],"our":[124],"proposed":[125],"method":[126],"competing":[128],"or":[130],"surpassing":[131],"performance":[133],"some":[135],"strong":[136],"baselines":[137],"multiple":[139],"MiniGrid":[140],"environments.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}