{"id":"https://openalex.org/W4241383739","doi":"https://doi.org/10.1109/his.2012.6421387","title":"Adaptive function approximation in reinforcement learning with an interpolating growing neural gas","display_name":"Adaptive function approximation in reinforcement learning with an interpolating growing neural gas","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W4241383739","doi":"https://doi.org/10.1109/his.2012.6421387"},"language":"en","primary_location":{"id":"doi:10.1109/his.2012.6421387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/his.2012.6421387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th International Conference on Hybrid Intelligent Systems (HIS)","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/A5101847583","display_name":"Michael Baumann","orcid":"https://orcid.org/0000-0001-7692-5913"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Michael Baumann","raw_affiliation_strings":["International Graduate School of Dynamic Intelligent Systems, University of Paderborn, Paderborn, Germany"],"affiliations":[{"raw_affiliation_string":"International Graduate School of Dynamic Intelligent Systems, University of Paderborn, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037967044","display_name":"Hans Kleine B\u00fcning","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hans Kleine Buning","raw_affiliation_strings":["Department of Computer Science, University of Paderborn, Paderborn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Paderborn, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101847583"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.40707739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"7","issue":null,"first_page":"512","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10320","display_name":"Neural Networks and Applications","score":0.9914000034332275,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8508884906768799},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.6915386319160461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6571059823036194},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6302087306976318},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.564548671245575},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5558743476867676},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5528928637504578},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5072583556175232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4871084690093994},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45685842633247375},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4308532178401947},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4305878281593323},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3534303903579712},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3406899571418762},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2861509621143341},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2238181233406067},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.13094466924667358}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8508884906768799},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.6915386319160461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6571059823036194},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6302087306976318},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.564548671245575},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5558743476867676},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5528928637504578},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5072583556175232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4871084690093994},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45685842633247375},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4308532178401947},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4305878281593323},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3534303903579712},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3406899571418762},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2861509621143341},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2238181233406067},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.13094466924667358},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/his.2012.6421387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/his.2012.6421387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th International Conference on Hybrid Intelligent Systems (HIS)","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":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W51508254","https://openalex.org/W1548867233","https://openalex.org/W1820996291","https://openalex.org/W1980972971","https://openalex.org/W2018500972","https://openalex.org/W2084838588","https://openalex.org/W2106261932","https://openalex.org/W2107977784","https://openalex.org/W2113913482","https://openalex.org/W2116339921","https://openalex.org/W2125074935","https://openalex.org/W2130304665","https://openalex.org/W2137269967","https://openalex.org/W2138754805","https://openalex.org/W2147169375","https://openalex.org/W2541498929","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4248400504","https://openalex.org/W6602057636","https://openalex.org/W6633104037","https://openalex.org/W6677193802","https://openalex.org/W6678545291","https://openalex.org/W6680294583"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W4225571923","https://openalex.org/W2166117066","https://openalex.org/W3212257828","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2999580272","https://openalex.org/W2136202932","https://openalex.org/W4376605461"],"abstract_inverted_index":{"Q-Learning":[0,31,56],"is":[1,24,88,129,161,193],"a":[2,53,74,84,115,121,127],"widely":[3],"used":[4],"method":[5,160],"for":[6,51,143],"dealing":[7],"with":[8,67,83,172,196],"reinforcement":[9,64],"learning":[10,15,65],"problems.":[11],"To":[12],"speed":[13,155],"up":[14,156],"and":[16,32,57,71,119,167,190],"to":[17,27,30,39,124,146,154],"exploit":[18],"gained":[19],"experience":[20,38],"more":[21],"efficiently":[22],"it":[23],"highly":[25,183],"beneficial":[26],"add":[28],"generalization":[29],"thus":[33],"enabling":[34],"the":[35,78,99,111,147,168,181,185,188],"transfer":[36],"of":[37,55,77,187],"unseen":[40],"but":[41],"similar":[42],"states.":[43],"In":[44],"this":[45,135],"paper,":[46],"we":[47,132,150],"report":[48],"on":[49,92],"improvements":[50],"GNG-Q,":[52],"combination":[54],"growing":[58],"neural":[59],"gas":[60],"(GNG).":[61],"It":[62],"solves":[63],"problems":[66],"continuous":[68,164],"state":[69,79,165],"spaces":[70,166],"simultaneously":[72],"learns":[73],"proper":[75],"approximation":[76,189],"space":[80],"by":[81],"starting":[82],"coarse":[85],"resolution":[86],"that":[87,103,134,180,191],"gradually":[89],"refined":[90],"based":[91],"information":[93],"achieved":[94],"during":[95],"learning.":[96,157],"We":[97],"introduce":[98],"Interpolating":[100],"GNG-Q":[101],"(IGNG-Q)":[102],"uses":[104],"distance-based":[105],"interpolation":[106],"between":[107],"learned":[108],"Q-vectors,":[109],"adjust":[110],"update":[112],"rule,":[113],"suggest":[114],"new":[116,122],"refinement":[117,128],"strategy":[118],"propose":[120],"criterion":[123,136],"decide":[125],"when":[126],"necessary.":[130],"Furthermore,":[131],"argue":[133],"offers":[137],"an":[138],"implicit":[139],"local":[140],"stopping":[141],"condition":[142],"changes":[144],"made":[145],"approximation.":[148],"Additionally,":[149],"employ":[151],"eligibility":[152],"traces":[153],"The":[158],"improved":[159],"evaluated":[162],"in":[163],"results":[169],"are":[170],"compared":[171],"several":[173],"approaches":[174],"from":[175],"literature.":[176],"Our":[177],"experiments":[178],"confirm":[179],"modifications":[182],"improve":[184],"efficiency":[186],"IGNG-Q":[192],"well":[194],"competitive":[195],"existing":[197],"methods.":[198]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}