{"id":"https://openalex.org/W2325530481","doi":"https://doi.org/10.1109/devlrn.2014.6982996","title":"Extending cortical-basal inspired reinforcement learning model with success-failure experience","display_name":"Extending cortical-basal inspired reinforcement learning model with success-failure experience","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2325530481","doi":"https://doi.org/10.1109/devlrn.2014.6982996","mag":"2325530481"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2014.6982996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2014.6982996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Development and Learning and on Epigenetic Robotics","raw_type":"proceedings-article"},"type":"article","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/A5006168104","display_name":"Shoubhik Debnath","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127444","display_name":"Fraunhofer Institute for Cognitive Systems","ror":"https://ror.org/02fez3815","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127444","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Shoubhik Debnath","raw_affiliation_strings":["Institute for Cognitive Systems, Technical University Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Cognitive Systems, Technical University Munich, Munich, Germany","institution_ids":["https://openalex.org/I4210127444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004620662","display_name":"John Nassour","orcid":"https://orcid.org/0000-0002-7208-1271"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"John Nassour","raw_affiliation_strings":["Artificial Intelligence, Computer Science Chemnitz University of Technology, Chemnitz, Germany"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence, Computer Science Chemnitz University of Technology, Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006168104"],"corresponding_institution_ids":["https://openalex.org/I4210127444"],"apc_list":null,"apc_paid":null,"fwci":0.1531,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53749808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"173","issue":null,"first_page":"293","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9988999962806702,"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":0.9988999962806702,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9973000288009644,"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9943000078201294,"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":0.8841766715049744},{"id":"https://openalex.org/keywords/orbitofrontal-cortex","display_name":"Orbitofrontal cortex","score":0.7534831166267395},{"id":"https://openalex.org/keywords/anterior-cingulate-cortex","display_name":"Anterior cingulate cortex","score":0.6623361110687256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6485591530799866},{"id":"https://openalex.org/keywords/neurocognitive","display_name":"Neurocognitive","score":0.48470377922058105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4475572109222412},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44000911712646484},{"id":"https://openalex.org/keywords/cortex","display_name":"Cortex (anatomy)","score":0.43841981887817383},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4209914803504944},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.37551456689834595},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.3168296217918396},{"id":"https://openalex.org/keywords/prefrontal-cortex","display_name":"Prefrontal cortex","score":0.2085893750190735},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.11608922481536865},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09742701053619385}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8841766715049744},{"id":"https://openalex.org/C2776559556","wikidata":"https://www.wikidata.org/wiki/Q18717","display_name":"Orbitofrontal cortex","level":4,"score":0.7534831166267395},{"id":"https://openalex.org/C2778402161","wikidata":"https://www.wikidata.org/wiki/Q2121931","display_name":"Anterior cingulate cortex","level":3,"score":0.6623361110687256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485591530799866},{"id":"https://openalex.org/C172467417","wikidata":"https://www.wikidata.org/wiki/Q1670397","display_name":"Neurocognitive","level":3,"score":0.48470377922058105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4475572109222412},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44000911712646484},{"id":"https://openalex.org/C2777348757","wikidata":"https://www.wikidata.org/wiki/Q2346577","display_name":"Cortex (anatomy)","level":2,"score":0.43841981887817383},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4209914803504944},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37551456689834595},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.3168296217918396},{"id":"https://openalex.org/C2781195155","wikidata":"https://www.wikidata.org/wiki/Q18680","display_name":"Prefrontal cortex","level":3,"score":0.2085893750190735},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.11608922481536865},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09742701053619385},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2014.6982996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2014.6982996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Development and Learning and on Epigenetic Robotics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1776271027","https://openalex.org/W1971976749","https://openalex.org/W1979603435","https://openalex.org/W2000164389","https://openalex.org/W2005391856","https://openalex.org/W2010222763","https://openalex.org/W2023057624","https://openalex.org/W2046102525","https://openalex.org/W2081357085","https://openalex.org/W2085755382","https://openalex.org/W2094619218","https://openalex.org/W2115494899","https://openalex.org/W2117726420","https://openalex.org/W2119170562","https://openalex.org/W2128211763","https://openalex.org/W2128562176","https://openalex.org/W2141385700","https://openalex.org/W2153562927","https://openalex.org/W2159254339","https://openalex.org/W2747420047","https://openalex.org/W4214717370","https://openalex.org/W4235391064","https://openalex.org/W6638039232"],"related_works":["https://openalex.org/W3185423717","https://openalex.org/W2768412208","https://openalex.org/W3091630195","https://openalex.org/W2010222763","https://openalex.org/W4385741981","https://openalex.org/W2162681207","https://openalex.org/W2765207801","https://openalex.org/W1524661139","https://openalex.org/W2488838968","https://openalex.org/W4282829590"],"abstract_inverted_index":{"Neurocognitive":[0],"studies":[1],"showed":[2,175],"that":[3,30,43,92,119],"neurons":[4,31],"of":[5,13,53,65,83,97,163,186,190],"the":[6,19,24,33,57,62,69,73,81,84,103,121,128,152,160,169,179,194],"orbitofrontal":[7,70],"cortex":[8,36,71],"get":[9],"activated":[10],"for":[11],"expectation":[12],"immediate":[14],"reward.":[15],"Therefore":[16],"they":[17],"are":[18],"key":[20],"reward":[21],"structure":[22],"in":[23,32,56,148,184],"brain.":[25],"It":[26],"was":[27,130,156],"also":[28],"shown":[29],"anterior":[34,74],"cingulate":[35,75],"work":[37],"as":[38],"an":[39,50,88,138],"early":[40],"warning":[41],"system":[42],"prevents":[44],"repeating":[45],"mistakes.":[46,111],"This":[47],"paper":[48],"introduces":[49],"extended":[51],"model":[52,155],"reinforcement":[54],"learning":[55,161,191],"cortex-basal":[58],"ganglia":[59],"network":[60],"by":[61,95,108,145,168],"hypothetical":[63],"involvement":[64],"two":[66],"cortical":[67],"regions,":[68],"and":[72,99,188],"cortex.":[76],"In":[77],"order":[78],"to":[79,105,115,123,132,141,158,165],"prove":[80],"effectiveness":[82],"approach,":[85],"we":[86],"propose":[87],"enhanced":[89,180],"actor-critic":[90,181,196],"method":[91,129,182],"is":[93],"guided":[94],"experiences":[96,113],"success":[98],"failure.":[100],"Failures":[101],"help":[102],"agent":[104,122,139],"explore":[106],"regions":[107,118],"avoiding":[109,146],"past":[110],"Successful":[112],"allow":[114],"exploit":[116],"those":[117],"guarantee":[120],"reach":[124,142],"its":[125,143,149],"goal.":[126],"First,":[127],"applied":[131],"a":[133],"2-D":[134],"grid":[135],"problem,":[136],"where":[137],"had":[140],"goal":[144],"obstacles":[147],"path.":[150],"Second,":[151],"proposed":[153],"RL":[154],"used":[157],"optimize":[159],"policy":[162],"how":[164],"play":[166],"bowling":[167],"NAO":[170],"humanoid":[171],"robot.":[172],"The":[173],"results":[174],"significant":[176],"improvement":[177],"using":[178],"both":[183],"terms":[185],"performance":[187],"rate":[189],"compared":[192],"with":[193],"standard":[195],"method.":[197]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
