{"id":"https://openalex.org/W2910885512","doi":"https://doi.org/10.1109/iros.2018.8594017","title":"A Bio-inspired Reinforcement Learning Rule to Optimise Dynamical Neural Networks for Robot Control","display_name":"A Bio-inspired Reinforcement Learning Rule to Optimise Dynamical Neural Networks for Robot Control","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2910885512","doi":"https://doi.org/10.1109/iros.2018.8594017","mag":"2910885512"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8594017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/44714b66-d87b-4466-ae1a-e23f3f9e0d63","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006975423","display_name":"Tianqi Wei","orcid":"https://orcid.org/0000-0002-9602-4861"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tianqi Wei","raw_affiliation_strings":["Stokes Research Group, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stokes Research Group, University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066496499","display_name":"Barbara Webb","orcid":"https://orcid.org/0000-0002-8336-6926"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Barbara Webb","raw_affiliation_strings":["Institute of Perception, Action and Behaviour, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Perception, Action and Behaviour, University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"556","last_page":"561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9962000250816345,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular 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/artificial-neural-network","display_name":"Artificial neural network","score":0.689731240272522},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6790996789932251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6290863752365112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.626442015171051},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5362687706947327},{"id":"https://openalex.org/keywords/learning-rule","display_name":"Learning rule","score":0.496905118227005},{"id":"https://openalex.org/keywords/dynamical-systems-theory","display_name":"Dynamical systems theory","score":0.4242631196975708},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4205319881439209},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3275521397590637}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.689731240272522},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6790996789932251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6290863752365112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626442015171051},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5362687706947327},{"id":"https://openalex.org/C2779127903","wikidata":"https://www.wikidata.org/wiki/Q6510194","display_name":"Learning rule","level":3,"score":0.496905118227005},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.4242631196975708},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4205319881439209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3275521397590637},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2018.8594017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/44714b66-d87b-4466-ae1a-e23f3f9e0d63","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/44714b66-d87b-4466-ae1a-e23f3f9e0d63","pdf_url":"http://hdl.handle.net/20.500.11820/44714b66-d87b-4466-ae1a-e23f3f9e0d63","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/44714b66-d87b-4466-ae1a-e23f3f9e0d63","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/44714b66-d87b-4466-ae1a-e23f3f9e0d63","pdf_url":"http://hdl.handle.net/20.500.11820/44714b66-d87b-4466-ae1a-e23f3f9e0d63","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2910885512.pdf","grobid_xml":"https://content.openalex.org/works/W2910885512.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W44204917","https://openalex.org/W1576838367","https://openalex.org/W1978458868","https://openalex.org/W1984465702","https://openalex.org/W2009375605","https://openalex.org/W2018643157","https://openalex.org/W2048494783","https://openalex.org/W2053957473","https://openalex.org/W2091849927","https://openalex.org/W2156174987","https://openalex.org/W2286435172","https://openalex.org/W2575705757","https://openalex.org/W2736506089","https://openalex.org/W2764174595","https://openalex.org/W2774113336","https://openalex.org/W2887369211","https://openalex.org/W2963589288","https://openalex.org/W3037207827","https://openalex.org/W6601750520"],"related_works":["https://openalex.org/W1662842982","https://openalex.org/W4319083788","https://openalex.org/W2103581399","https://openalex.org/W3022038857","https://openalex.org/W1629725936","https://openalex.org/W4360764167","https://openalex.org/W2963561234","https://openalex.org/W4318621078","https://openalex.org/W3095449511","https://openalex.org/W3162151154"],"abstract_inverted_index":{"Most":[0],"approaches":[1],"for":[2],"optimisation":[3],"of":[4,11,33,60,78],"neural":[5,23,37,107],"networks":[6,24],"are":[7,27,39],"based":[8],"on":[9,93],"variants":[10],"back-propagation.":[12],"This":[13],"requires":[14],"the":[15,31,56,74,89,120],"network":[16,64,85],"to":[17,45,80,82,124],"be":[18],"time":[19],"invariant":[20],"and":[21,58,69,76,115,118],"differentiable;":[22],"with":[25],"dynamics":[26,59],"thus":[28],"generally":[29],"outside":[30],"scope":[32],"these":[34],"methods.":[35],"Biological":[36],"circuits":[38],"highly":[40],"dynamic":[41],"yet":[42],"clearly":[43],"able":[44],"support":[46],"learning.":[47],"We":[48,87],"propose":[49],"a":[50,70,83,94,100,105,109],"reinforcement":[51],"learning":[52,91],"approach":[53],"inspired":[54],"by":[55],"mechanisms":[57],"biological":[61],"synapses.":[62],"The":[63],"weights":[65],"undergo":[66],"spontaneous":[67],"fluctuations,":[68],"reward":[71],"signal":[72],"modulates":[73],"centre":[75],"amplitude":[77],"fluctuations":[79],"converge":[81],"desired":[84],"behaviour.":[86],"test":[88],"new":[90],"rule":[92],"2D":[95],"bipedal":[96],"walking":[97],"simulation,":[98],"using":[99],"control":[101],"system":[102],"that":[103],"combines":[104],"recurrent":[106],"network,":[108],"bio-inspired":[110],"central":[111],"pattern":[112],"generator":[113],"layer":[114],"proportional-integral":[116],"control,":[117],"demonstrate":[119],"first":[121],"successful":[122],"solution":[123],"this":[125],"benchmark":[126],"task.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}