{"id":"https://openalex.org/W3003051334","doi":"https://doi.org/10.1109/icra40945.2020.9197262","title":"On Simple Reactive Neural Networks for Behaviour-Based Reinforcement Learning","display_name":"On Simple Reactive Neural Networks for Behaviour-Based Reinforcement Learning","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3003051334","doi":"https://doi.org/10.1109/icra40945.2020.9197262","mag":"3003051334"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.07973","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011989897","display_name":"Ameya Pore","orcid":"https://orcid.org/0000-0001-7380-6118"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ameya Pore","raw_affiliation_strings":["Computer Vision and Autonomous group, School of Computing Science, University of Glasgow, UK","University of Glasgow,Computer Vision and Autonomous group, School of Computing Science,UK,G12 8QQ"],"affiliations":[{"raw_affiliation_string":"Computer Vision and Autonomous group, School of Computing Science, University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow,Computer Vision and Autonomous group, School of Computing Science,UK,G12 8QQ","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013549829","display_name":"Gerardo Arag\u00f3n-Camarasa","orcid":"https://orcid.org/0000-0003-3756-5569"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gerardo Aragon-Camarasa","raw_affiliation_strings":["Computer Vision and Autonomous group, School of Computing Science, University of Glasgow, UK","University of Glasgow,Computer Vision and Autonomous group, School of Computing Science,UK,G12 8QQ"],"affiliations":[{"raw_affiliation_string":"Computer Vision and Autonomous group, School of Computing Science, University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow,Computer Vision and Autonomous group, School of Computing Science,UK,G12 8QQ","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011989897"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":0.1371,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52314504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"7477","last_page":"7483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8217636346817017},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.7726562023162842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7171452045440674},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7056859731674194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995403170585632},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6444655060768127},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5748628377914429},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5447053909301758},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5180085301399231},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4872378408908844},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.4298836886882782},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3609420955181122},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32802873849868774},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1860640048980713}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8217636346817017},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7726562023162842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7171452045440674},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7056859731674194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995403170585632},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6444655060768127},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5748628377914429},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5447053909301758},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5180085301399231},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4872378408908844},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.4298836886882782},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3609420955181122},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32802873849868774},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1860640048980713},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra40945.2020.9197262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.07973","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.07973","pdf_url":"https://arxiv.org/pdf/2001.07973","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3003051334","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2001.07973","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2001.07973","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.07973","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.07973","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.07973","pdf_url":"https://arxiv.org/pdf/2001.07973","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1696371728","display_name":null,"funder_award_id":"EP/S019472/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1515851193","https://openalex.org/W1757796397","https://openalex.org/W1966089223","https://openalex.org/W1977655452","https://openalex.org/W2051891848","https://openalex.org/W2155307968","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2342840547","https://openalex.org/W2397253692","https://openalex.org/W2575705757","https://openalex.org/W2765602917","https://openalex.org/W2785693718","https://openalex.org/W2788862220","https://openalex.org/W2792404612","https://openalex.org/W2809668646","https://openalex.org/W2809762329","https://openalex.org/W2898436992","https://openalex.org/W2907537824","https://openalex.org/W2920961587","https://openalex.org/W2946970867","https://openalex.org/W2949604932","https://openalex.org/W2956709224","https://openalex.org/W2963099939","https://openalex.org/W2963376229","https://openalex.org/W2963403593","https://openalex.org/W3102636071","https://openalex.org/W6627932998","https://openalex.org/W6637967152","https://openalex.org/W6692846177","https://openalex.org/W6704559304","https://openalex.org/W6744935223","https://openalex.org/W6748306599","https://openalex.org/W6748599296","https://openalex.org/W6752089545","https://openalex.org/W6752431149","https://openalex.org/W6756103505","https://openalex.org/W6757380569","https://openalex.org/W6759871227","https://openalex.org/W6765131315","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3091277626","https://openalex.org/W2789102901","https://openalex.org/W1595483645","https://openalex.org/W2588790649","https://openalex.org/W2100370041","https://openalex.org/W2735268712","https://openalex.org/W2786916331","https://openalex.org/W2283777287","https://openalex.org/W2743199808","https://openalex.org/W2889878992","https://openalex.org/W2108689239","https://openalex.org/W2108970313","https://openalex.org/W2158150115","https://openalex.org/W2995237914","https://openalex.org/W2418837394","https://openalex.org/W2971655565","https://openalex.org/W2910219310","https://openalex.org/W3080495593","https://openalex.org/W2936382365","https://openalex.org/W3130336107"],"abstract_inverted_index":{"We":[0,70,91],"present":[1],"a":[2,28,42,87,96,106,112,120,179],"behaviour-based":[3],"reinforcement":[4,133],"learning":[5,134,144],"approach,":[6,52],"inspired":[7],"by":[8,37,189],"Brook's":[9],"subsumption":[10],"architecture,":[11],"in":[12,86,95,154,174,182],"which":[13,130,177],"simple":[14],"fully":[15],"connected":[16],"networks":[17],"are":[18],"trained":[19],"as":[20],"reactive":[21,49,64,84],"behaviours.":[22],"Our":[23,139],"working":[24],"assumption":[25],"is":[26,103,152],"that":[27,142],"pick":[29,170],"and":[30,47,54,79,108,156,171,196],"place":[31,172],"robotic":[32,143],"task":[33,102,173],"can":[34,145],"be":[35,146],"simplified":[36],"leveraging":[38],"domain":[39],"knowledge":[40],"of":[41,82,129,185],"robotics":[43],"developer":[44],"to":[45,62,75,111,137,160],"decompose":[46],"train":[48],"behaviours;":[50],"namely,":[51],"grasp,":[53],"retract.":[55],"Then":[56],"the":[57,77,83,101,117,162,169,183],"robot":[58,98],"autonomously":[59],"learns":[60,168],"how":[61],"combine":[63],"behaviours":[65,85],"via":[66],"an":[67,72,126,190],"Actor-Critic":[68,73],"architecture.":[69],"use":[71],"policy":[74],"determine":[76],"activation":[78],"inhibition":[80],"mechanisms":[81],"particular":[88],"temporal":[89],"sequence.":[90],"validate":[92],"our":[93,166],"approach":[94,167,192],"simulated":[97],"environment":[99],"where":[100],"about":[104],"picking":[105],"block":[107],"taking":[109],"it":[110],"target":[113],"position":[114],"while":[115],"orienting":[116],"gripper":[118],"from":[119],"top":[121],"grasp.":[122],"The":[123],"latter":[124],"represents":[125,178],"extra":[127],"degree-of-freedom":[128],"current":[131],"end-to-end":[132,191],"approaches":[135],"fail":[136],"generalise.":[138],"findings":[140],"suggest":[141],"more":[147],"effective":[148],"if":[149],"each":[150],"behaviour":[151],"learnt":[153],"isolation":[155],"then":[157],"combined":[158],"them":[159],"accomplish":[161],"task.":[163],"That":[164],"is,":[165],"8,000":[175],"episodes,":[176],"drastic":[180],"reduction":[181],"number":[184],"training":[186],"episodes":[187],"required":[188],"(":[193],"95,000":[194],"episodes)":[195],"existing":[197],"state-of-the-art":[198],"algorithms.":[199]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}