{"id":"https://openalex.org/W2969069294","doi":"https://doi.org/10.1109/cec.2019.8789988","title":"Improving Reinforcement FALCON Learning in Complex Environment with Much Delayed Evaluation via Memetic Automaton","display_name":"Improving Reinforcement FALCON Learning in Complex Environment with Much Delayed Evaluation via Memetic Automaton","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2969069294","doi":"https://doi.org/10.1109/cec.2019.8789988","mag":"2969069294"},"language":"en","primary_location":{"id":"doi:10.1109/cec.2019.8789988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2019.8789988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Congress on Evolutionary Computation (CEC)","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/A5005174710","display_name":"Gengzhi Zhang","orcid":"https://orcid.org/0009-0009-7960-2605"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gengzhi Zhang","raw_affiliation_strings":["College of Computer Science, Chongqing University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051395807","display_name":"Liang Feng","orcid":"https://orcid.org/0000-0002-8356-7242"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Feng","raw_affiliation_strings":["College of Computer Science, Chongqing University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054330455","display_name":"Yuling Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuling Xie","raw_affiliation_strings":["Chongqing University Industrial Technology Research Institute, China"],"affiliations":[{"raw_affiliation_string":"Chongqing University Industrial Technology Research Institute, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086911362","display_name":"Zhou Wu","orcid":"https://orcid.org/0000-0002-8980-4210"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Wu","raw_affiliation_strings":["School of Automation, Chongqing University, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Chongqing University, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002133706","display_name":"Chen Lin","orcid":"https://orcid.org/0000-0001-6261-8509"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005174710"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56384707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"166","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9983000159263611,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9919000267982483,"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":0.8786696195602417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7516689896583557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5692216157913208},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5184863805770874},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4964795708656311},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.4797329008579254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4339732825756073},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.4212193191051483},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34406474232673645},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09128057956695557}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8786696195602417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516689896583557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5692216157913208},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5184863805770874},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4964795708656311},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.4797329008579254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4339732825756073},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.4212193191051483},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34406474232673645},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09128057956695557},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cec.2019.8789988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2019.8789988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Congress on Evolutionary Computation (CEC)","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":24,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W659473080","https://openalex.org/W1515851193","https://openalex.org/W1549212765","https://openalex.org/W2006134516","https://openalex.org/W2031801005","https://openalex.org/W2056356393","https://openalex.org/W2073320424","https://openalex.org/W2104274529","https://openalex.org/W2107726111","https://openalex.org/W2124175081","https://openalex.org/W2135774416","https://openalex.org/W2154047522","https://openalex.org/W2155262811","https://openalex.org/W2159536053","https://openalex.org/W2167867633","https://openalex.org/W2210407830","https://openalex.org/W2586101872","https://openalex.org/W2624262714","https://openalex.org/W2787205779","https://openalex.org/W4285719527","https://openalex.org/W6633013606","https://openalex.org/W6678114464","https://openalex.org/W6748554002"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2288872327","https://openalex.org/W3196817267","https://openalex.org/W2489338148","https://openalex.org/W2124961391","https://openalex.org/W1976600725","https://openalex.org/W576785828","https://openalex.org/W4388511637","https://openalex.org/W2074131991","https://openalex.org/W2733919410"],"abstract_inverted_index":{"The":[0],"Fusion":[1],"Architecture":[2],"for":[3,207],"Learning,":[4],"COgnition,":[5],"and":[6,32,35,204],"Navigation":[7],"(FALCON)":[8],"is":[9,87,135,177],"an":[10],"extension":[11],"of":[12,43,92,131,158,191,196,201,228,236,250],"the":[13,41,48,53,71,75,81,90,93,98,110,118,124,129,144,156,167,188,194,198,214,225,242,248,251],"self-organizing":[14],"neural":[15],"network":[16],"i.e.,":[17],"Adaptive":[18],"Resonance":[19],"Theory":[20],"(ART),":[21],"which":[22,55],"has":[23,67,139],"been":[24,68,140],"successfully":[25],"applied":[26],"in":[27,61,70,123,148,160,171,193,220,231],"many":[28,62],"reinforcement":[29,44,111,145,168],"learning":[30,38,42,147,170,226],"tasks,":[31],"demonstrated":[33],"fast":[34],"stable":[36],"real-time":[37],"capabilities.":[39],"However,":[40],"FALCON":[45,112,146,169,229,237],"relies":[46,96],"on":[47,97],"positive":[49,175],"feedbacks":[50],"obtained":[51],"from":[52,101,155,217],"environment,":[54],"may":[56,113],"not":[57,88],"be":[58,114],"always":[59],"available":[60],"real-world":[63],"applications.":[64],"Although":[65],"TD-FALCON":[66],"proposed":[69,252],"literature,":[72],"to":[73,79,116,121,142,165,179,212,223],"integrate":[74],"temporal":[76],"difference":[77],"method":[78],"estimate":[80],"payoff":[82],"value":[83],"when":[84],"immediate":[85],"reward":[86,176],"available,":[89],"accuracy":[91],"estimation":[94],"also":[95],"received":[99],"feedback":[100],"environment.":[102,150,233],"In":[103,184],"complex":[104,172,232],"environments":[105],"with":[106],"much":[107],"delayed":[108],"evaluation,":[109],"hard":[115,178],"learn":[117],"proper":[119],"knowledge":[120,215],"adapt":[122],"given":[125],"task":[126,245],"quickly.":[127],"To":[128],"best":[130],"our":[132],"knowledge,":[133],"there":[134],"no":[136],"existing":[137],"work":[138],"conducted":[141],"improve":[143,166,224],"such":[149],"Taking":[151],"this":[152,161],"cue,":[153],"inspired":[154],"science":[157],"memetics,":[159],"paper,":[162],"we":[163],"propose":[164],"environment":[173,222],"where":[174],"achieve,":[180],"via":[181],"memetic":[182,253],"automaton.":[183],"particular,":[185],"by":[186],"defining":[187],"particular":[189],"representation":[190],"memes":[192],"context":[195],"FALCON,":[197],"corresponding":[199],"designs":[200],"meme":[202,205,208,216],"selection":[203],"transmission":[206],"evolution":[209],"are":[210],"presented,":[211],"transfer":[213],"well-learned":[218],"agents":[219,230],"simple":[221],"performance":[227],"Lastly,":[234],"simulations":[235],"based":[238],"multi-agent":[239],"system":[240],"using":[241],"mine":[243],"navigation":[244],"platform,":[246],"confirmed":[247],"efficacy":[249],"model.":[254]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}