{"id":"https://openalex.org/W2890480185","doi":"https://doi.org/10.1109/icra.2018.8461241","title":"Speeding Up Incremental Learning Using Data Efficient Guided Exploration","display_name":"Speeding Up Incremental Learning Using Data Efficient Guided Exploration","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2890480185","doi":"https://doi.org/10.1109/icra.2018.8461241","mag":"2890480185"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8461241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/f4109968-2648-4083-807b-a1076bc4acf1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047209845","display_name":"Murtaza Hazara","orcid":"https://orcid.org/0000-0003-0477-3767"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Murtaza Hazara","raw_affiliation_strings":["Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080940147","display_name":"Ville Kyrki","orcid":"https://orcid.org/0000-0002-5230-5549"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Kyrki","raw_affiliation_strings":["Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047209845"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.5574,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6526073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"5082","last_page":"5089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.7541402578353882},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6819272041320801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6808622479438782},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6153307557106018},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5712509155273438},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4636728763580322},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.4582459628582001},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3237186670303345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13672950863838196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541402578353882},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6819272041320801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6808622479438782},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6153307557106018},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5712509155273438},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4636728763580322},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4582459628582001},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3237186670303345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13672950863838196},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra.2018.8461241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/36319","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/f4109968-2648-4083-807b-a1076bc4acf1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/36319","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/f4109968-2648-4083-807b-a1076bc4acf1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1481251645","https://openalex.org/W1670925118","https://openalex.org/W1976536305","https://openalex.org/W2012204020","https://openalex.org/W2012392077","https://openalex.org/W2022638737","https://openalex.org/W2069324174","https://openalex.org/W2098524868","https://openalex.org/W2110304639","https://openalex.org/W2116226448","https://openalex.org/W2133853511","https://openalex.org/W2202850001","https://openalex.org/W2594639291","https://openalex.org/W2737943148","https://openalex.org/W2751554013","https://openalex.org/W4211049957","https://openalex.org/W4237733001","https://openalex.org/W4300982816","https://openalex.org/W6653435097","https://openalex.org/W6682093400"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3162204513","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548"],"abstract_inverted_index":{"To":[0],"cope":[1],"with":[2,77,175,214,259],"varying":[3],"conditions,":[4],"motor":[5],"primitives":[6,18],"(MPs)":[7],"must":[8],"support":[9],"generalization":[10,44],"over":[11,254],"task":[12,37,178],"parameters":[13],"to":[14,35,94],"avoid":[15],"learning":[16,66,108,113,252],"separate":[17],"for":[19,32,100,120,139,142,150,158,167],"each":[20],"situation.":[21],"In":[22],"this":[23],"regard,":[24],"deterministic":[25],"and":[26,97,164,191],"probabilistic":[27,48],"models":[28,49,60,190],"have":[29],"been":[30,51],"proposed":[31,131,231],"generalizing":[33,140],"MPs":[34,46,141,172],"new":[36,143],"parameters,":[38],"thus":[39,80],"providing":[40],"limited":[41],"generalization.":[42],"Although":[43],"of":[45,105,124,129,162,171,198,211,240,251,262],"using":[47],"has":[50,205],"studied,":[52],"it":[53,99],"is":[54,75],"not":[55],"clear":[56],"how":[57],"such":[58],"generalizable":[59],"can":[61,67],"be":[62,68],"learned":[63],"efficiently.":[64],"Reinforcement":[65],"more":[69],"efficient":[70],"when":[71],"the":[72,102,130,152,160,169,181,202,208,220,226,230,237,241],"exploration":[73,83,103,238],"process":[74,104,239],"tuned":[76],"data":[78],"uncertainty,":[79],"reducing":[81],"unnecessary":[82],"in":[84,196],"a":[85,116,122,134,145,176,260],"data-efficient":[86],"way.":[87],"We":[88],"propose":[89],"an":[90,106],"empirical":[91,165,232],"Bayes":[92,166,233],"method":[93],"predict":[95],"uncertainty":[96,170,227],"utilize":[98],"guiding":[101],"incremental":[107,112],"framework.":[109],"The":[110,126,245],"online":[111],"framework":[114,132],"uses":[115],"single":[117],"human":[118],"demonstration":[119],"constructing":[121],"database":[123],"MPs.":[125],"main":[127],"ingredients":[128],"are":[133],"global":[135,182],"parametric":[136],"model":[137,156,184,203],"(GPDMP)":[138],"situations,":[144],"model-free":[146,242],"policy":[147,243],"search":[148],"agent":[149],"optimizing":[151],"failed":[153],"predicted":[154,228],"MPs,":[155],"selection":[157,204],"controlling":[159],"complexity":[161,210],"GPDMp,":[163],"extracting":[168],"prediction.":[173],"Experiments":[174],"ball-in-a-cup":[177],"demonstrate":[179],"that":[180],"GPDMP":[183,212],"generalizes":[185],"significantly":[186],"better":[187],"than":[188],"linear":[189],"Locally":[192],"Weighted":[193],"Regression":[194],"especially":[195],"terms":[197],"extrapolation":[199],"capability.":[200],"Furthermore,":[201],"successfully":[206,235],"identified":[207],"required":[209],"even":[213],"few":[215],"training":[216],"samples":[217],"while":[218],"satisfying":[219],"Occam":[221],"Razor's":[222],"prinicple.":[223],"Above":[224],"all,":[225],"by":[229],"approach":[234],"guided":[236],"search.":[244],"experiments":[246],"indicated":[247],"statistically":[248],"significant":[249],"improvement":[250],"speed":[253],"covariance":[255],"matrix":[256],"adaptation":[257],"(CMA)":[258],"significance":[261],"p=0.002.":[263]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}