{"id":"https://openalex.org/W2536057734","doi":"https://doi.org/10.1109/devlrn.2012.6400808","title":"Multi-optima exploration with adaptive Gaussian mixture model","display_name":"Multi-optima exploration with adaptive Gaussian mixture model","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2536057734","doi":"https://doi.org/10.1109/devlrn.2012.6400808","mag":"2536057734"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2012.6400808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2012.6400808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","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/A5048780399","display_name":"Sylvain Calinon","orcid":"https://orcid.org/0000-0002-9036-6799"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Sylvain Calinon","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084599286","display_name":"Affan Pervez","orcid":"https://orcid.org/0000-0001-8005-5949"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Affan Pervez","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044243940","display_name":"Darwin G. Caldwell","orcid":"https://orcid.org/0000-0002-6233-9961"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Darwin G. Caldwell","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT), Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048780399"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":2.1407,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89386345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9783999919891357,"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":0.9783999919891357,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9704999923706055,"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/computer-science","display_name":"Computer science","score":0.6676616668701172},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6646260023117065},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6146560311317444},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.48035773634910583},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4481184780597687},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4449050724506378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3862682282924652},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34136271476745605},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.291602224111557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23461860418319702}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6676616668701172},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6646260023117065},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6146560311317444},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.48035773634910583},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4481184780597687},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4449050724506378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3862682282924652},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34136271476745605},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.291602224111557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23461860418319702},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2012.6400808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2012.6400808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","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":27,"referenced_works":["https://openalex.org/W102487131","https://openalex.org/W1502364872","https://openalex.org/W1530191702","https://openalex.org/W1824988365","https://openalex.org/W1925816294","https://openalex.org/W1976207411","https://openalex.org/W1977013839","https://openalex.org/W2003136661","https://openalex.org/W2004191624","https://openalex.org/W2015130184","https://openalex.org/W2047191624","https://openalex.org/W2071841410","https://openalex.org/W2080039641","https://openalex.org/W2090528409","https://openalex.org/W2098524868","https://openalex.org/W2118292158","https://openalex.org/W2120070743","https://openalex.org/W2124172617","https://openalex.org/W2124975726","https://openalex.org/W2127572219","https://openalex.org/W2133853511","https://openalex.org/W2142916680","https://openalex.org/W3005581722","https://openalex.org/W4285719527","https://openalex.org/W6631684746","https://openalex.org/W6640290305","https://openalex.org/W6674872077"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2992415251","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2962839548","https://openalex.org/W3138923328","https://openalex.org/W1992295166","https://openalex.org/W2143508933"],"abstract_inverted_index":{"In":[0],"learning":[1,8],"by":[2,59,106,239],"exploration":[3,61,135],"problems":[4],"such":[5,72,237],"as":[6,62,73,158,176],"reinforcement":[7],"(RL),":[9],"direct":[10],"policy":[11,45,57,147],"search,":[12],"stochastic":[13],"optimization":[14,179],"or":[15],"evolutionary":[16],"computation,":[17],"the":[18,49,53,86,91,96,126,134,153,182,191,196,205,215,219,230,247],"goal":[19],"of":[20,28,51,55,77,117,128,136,141,155,249],"an":[21,114],"agent":[22],"is":[23,149,168,200],"to":[24,41,84,103,145,151,194,202,243,246],"maximize":[25],"some":[26],"form":[27],"reward":[29],"function":[30],"(or":[31],"minimize":[32],"a":[33,43,63,108,122,163,171,177],"cost":[34],"function).":[35],"Often,":[36],"these":[37],"algorithms":[38],"are":[39],"designed":[40],"find":[42],"single":[44],"solution.":[46],"We":[47,93],"address":[48],"problem":[50],"representing":[52,125],"space":[54,127,154,161],"control":[56,130],"solutions":[58,88],"considering":[60],"density":[64],"estimation":[65],"problem.":[66],"Such":[67],"representation":[68],"provides":[69],"additional":[70],"information":[71],"shape":[74],"and":[75,89,132],"curvature":[76],"local":[78],"peaks":[79],"that":[80,95,229],"can":[81,99,208,235],"be":[82,101],"exploited":[83],"analyze":[85],"discovered":[87],"guide":[90],"exploration.":[92],"show":[94,228],"search":[97,216,233],"process":[98],"easily":[100],"generalized":[102],"multi-peaked":[104],"distributions":[105],"employing":[107],"Gaussian":[109],"mixture":[110],"model":[111,152],"(GMM)":[112],"with":[113],"adaptive":[115],"number":[116],"components.":[118],"The":[119,166,226],"GMM":[120],"has":[121],"dual":[123],"role:":[124],"possible":[129,156],"policies,":[131],"guiding":[133],"new":[137,210],"policies.":[138],"A":[139],"variation":[140],"expectation-maximization":[142],"(EM)":[143],"applied":[144],"reward-weighted":[146],"parameters":[148],"presented":[150],"solutions,":[157],"if":[159],"this":[160],"was":[162],"probability":[164],"distribution.":[165],"approach":[167,207,234],"tested":[169],"in":[170,214],"dart":[172],"game":[173],"experiment":[174,199],"formulated":[175],"black-box":[178],"problem,":[180],"where":[181],"agent's":[183],"throwing":[184],"capability":[185],"increases":[186],"while":[187],"it":[188],"chases":[189],"for":[190],"best":[192],"strategy":[193],"play":[195],"game.":[197],"This":[198],"used":[201],"study":[203],"how":[204],"proposed":[206,231],"exploit":[209],"promising":[211,241],"solution":[212],"alternatives":[213],"process,":[217],"when":[218],"optimality":[220],"criterion":[221],"slowly":[222],"drifts":[223],"over":[224],"time.":[225],"results":[227],"multi-optima":[232],"anticipate":[236],"changes":[238],"exploiting":[240],"candidates":[242],"smoothly":[244],"adapt":[245],"change":[248],"global":[250],"optimum.":[251]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}