{"id":"https://openalex.org/W2220533764","doi":"https://doi.org/10.1109/humanoids.2015.7363529","title":"Regularized covariance estimation for weighted maximum likelihood policy search methods","display_name":"Regularized covariance estimation for weighted maximum likelihood policy search methods","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2220533764","doi":"https://doi.org/10.1109/humanoids.2015.7363529","mag":"2220533764"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2015.7363529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2015.7363529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Regularized_covariance_estimation_for_weighted_maximum_likelihood_policy_search_methods/25171190","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007133617","display_name":"Abbas Abdolmaleki","orcid":"https://orcid.org/0000-0001-6692-5856"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]},{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Abbas Abdolmaleki","raw_affiliation_strings":["DETI/IEETA, University of Aveiro, Aveiro, Portugal","DSI, University of Minho, Braga, Portugal","LIACC, University of Porto, Porto, Portugal"],"affiliations":[{"raw_affiliation_string":"DETI/IEETA, University of Aveiro, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"DSI, University of Minho, Braga, Portugal","institution_ids":["https://openalex.org/I99682543"]},{"raw_affiliation_string":"LIACC, University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055569781","display_name":"Nuno Lau","orcid":"https://orcid.org/0000-0003-0513-158X"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Lau","raw_affiliation_strings":["DETI/IEETA, University of Aveiro, Aveiro, Portugal"],"affiliations":[{"raw_affiliation_string":"DETI/IEETA, University of Aveiro, Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089812166","display_name":"Lu\u00eds Paulo Reis","orcid":"https://orcid.org/0000-0002-4709-1718"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Luis Paulo Reis","raw_affiliation_strings":["LIACC, University of Porto, Porto, Portugal"],"affiliations":[{"raw_affiliation_string":"LIACC, University of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110467801","display_name":"Gerhard Neumann","orcid":"https://orcid.org/0000-0002-5483-4225"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Neumann","raw_affiliation_strings":["CLAS, TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"CLAS, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007133617"],"corresponding_institution_ids":["https://openalex.org/I182534213","https://openalex.org/I60858718","https://openalex.org/I99682543"],"apc_list":null,"apc_paid":null,"fwci":4.4483,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94984547,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"154","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9932000041007996,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9932000041007996,"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/T10136","display_name":"Statistical Methods and Inference","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.961899995803833,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.7337257862091064},{"id":"https://openalex.org/keywords/maximum-likelihood-sequence-estimation","display_name":"Maximum likelihood sequence estimation","score":0.5959601998329163},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5831289291381836},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.545001208782196},{"id":"https://openalex.org/keywords/estimation-of-covariance-matrices","display_name":"Estimation of covariance matrices","score":0.5323315858840942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49898290634155273},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.486694872379303},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.43910861015319824},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3773100972175598},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3225330710411072},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09087949991226196}],"concepts":[{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.7337257862091064},{"id":"https://openalex.org/C191462741","wikidata":"https://www.wikidata.org/wiki/Q6795902","display_name":"Maximum likelihood sequence estimation","level":3,"score":0.5959601998329163},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5831289291381836},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.545001208782196},{"id":"https://openalex.org/C180877172","wikidata":"https://www.wikidata.org/wiki/Q5401390","display_name":"Estimation of covariance matrices","level":3,"score":0.5323315858840942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49898290634155273},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.486694872379303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43910861015319824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3773100972175598},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3225330710411072},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09087949991226196},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/humanoids.2015.7363529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2015.7363529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lincoln.ac.uk:25748","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196275","display_name":"Lincoln Repository (University of Lincoln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51532219","host_organization_name":"University of Lincoln","host_organization_lineage":["https://openalex.org/I51532219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop contribution"},{"id":"pmh:oai:figshare.com:article/25171190","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Regularized_covariance_estimation_for_weighted_maximum_likelihood_policy_search_methods/25171190","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/25171190","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Regularized_covariance_estimation_for_weighted_maximum_likelihood_policy_search_methods/25171190","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.5,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1567473651","https://openalex.org/W1925816294","https://openalex.org/W1929309940","https://openalex.org/W1990512452","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2039367850","https://openalex.org/W2098524868","https://openalex.org/W2111967991","https://openalex.org/W2123327324","https://openalex.org/W2123967136","https://openalex.org/W2130990842","https://openalex.org/W2138537392","https://openalex.org/W2151965738","https://openalex.org/W2172968643","https://openalex.org/W2296319761","https://openalex.org/W3005581722","https://openalex.org/W3007384386","https://openalex.org/W4250589301","https://openalex.org/W6640290305","https://openalex.org/W6653435097","https://openalex.org/W6653548176","https://openalex.org/W6674872077","https://openalex.org/W6676560026","https://openalex.org/W6678157427"],"related_works":["https://openalex.org/W2366184732","https://openalex.org/W1499442185","https://openalex.org/W2379466508","https://openalex.org/W2126916073","https://openalex.org/W1573889165","https://openalex.org/W2038723318","https://openalex.org/W1679731869","https://openalex.org/W2392411825","https://openalex.org/W3041177925","https://openalex.org/W1559074081"],"abstract_inverted_index":{"Many":[0],"episode-based":[1],"(or":[2],"direct)":[3],"policy":[4,143],"search":[5,13,88,144,178,187],"algorithms,":[6,26],"maintain":[7],"a":[8,35,118,136],"multivariate":[9],"Gaussian":[10],"distribution":[11,14,50,89,188],"as":[12,28],"over":[15],"the":[16,43,67,84,87,104,122,127,148,152,157,172,176,183,186,196],"parameter":[17],"space":[18],"of":[19,25,48,59,65,75,86,121,151,175,185],"some":[20],"objective":[21],"function.":[22],"One":[23],"class":[24],"such":[27],"episodic":[29],"REPS,":[30],"PoWER":[31],"or":[32],"PI2":[33],"uses,":[34],"weighted":[36],"maximum":[37,197],"likelihood":[38,198],"estimate":[39,125],"(WMLE)":[40],"to":[41,56,78,100],"update":[42],"mean":[44],"and":[45,62,126,156],"covariance":[46,60,80,106,124,129,138,154,159],"matrix":[47,107,139,155,160],"this":[49,102,132,181],"in":[51,111,162],"each":[52],"iteration.":[53,164],"However,":[54],"due":[55],"high":[57],"dimensionality":[58],"matrices":[61],"limited":[63],"number":[64],"samples,":[66],"WMLE":[68,76],"is":[69,168],"an":[70],"unreliable":[71],"estimator.":[72],"The":[73,165],"use":[74],"leads":[77],"over-fitted":[79],"estimates,":[81],"and,":[82],"hence":[83],"variance/entropy":[85],"decreases":[90],"too":[91],"quickly,":[92],"which":[93],"may":[94],"cause":[95],"premature":[96],"convergence.":[97],"In":[98,131],"order":[99],"alleviate":[101],"problem,":[103],"estimated":[105],"can":[108,189],"be":[109,190],"regularized":[110],"different":[112],"ways,":[113],"for":[114,142],"example":[115],"by":[116,170],"using":[117],"convex":[119,149],"combination":[120,150,166],"diagonal":[123],"sample":[128,153],"estimate.":[130,199],"paper,":[133],"we":[134],"propose":[135],"new":[137,177],"regularization":[140],"technique":[141],"methods":[145],"that":[146],"uses":[147],"old":[158],"used":[161],"last":[163],"weighting":[167],"determined":[169],"specifying":[171],"desired":[173],"entropy":[174,184],"distribution.":[179],"With":[180],"mechanism,":[182],"gradually":[191],"decreased":[192],"without":[193],"damage":[194],"from":[195]},"counts_by_year":[{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}