{"id":"https://openalex.org/W3195099242","doi":"https://doi.org/10.1007/s10458-021-09527-5","title":"Goal-driven active learning","display_name":"Goal-driven active learning","publication_year":2021,"publication_date":"2021-08-16","ids":{"openalex":"https://openalex.org/W3195099242","doi":"https://doi.org/10.1007/s10458-021-09527-5","mag":"3195099242"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-021-09527-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-021-09527-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-021-09527-5.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10458-021-09527-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069965217","display_name":"Nicolas Bougie","orcid":"https://orcid.org/0000-0001-9856-0038"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Nicolas Bougie","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","The Graduate University for Advanced Studies (Sokendai), Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9856-0038","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Studies (Sokendai), Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081854769","display_name":"Ryutaro Ichise","orcid":"https://orcid.org/0000-0001-8474-0150"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryutaro Ichise","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","The Graduate University for Advanced Studies (Sokendai), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Studies (Sokendai), Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069965217"],"corresponding_institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.13,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57677847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"35","issue":"2","first_page":null,"last_page":null},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9991999864578247,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9962999820709229,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8324847221374512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7660707235336304},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.719868540763855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6347876787185669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6159646511077881},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5993397235870361},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5890567302703857},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5114613771438599},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.510592520236969},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4897747039794922},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.46565109491348267},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45644786953926086},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4246925115585327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0973055362701416}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8324847221374512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660707235336304},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.719868540763855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6347876787185669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6159646511077881},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5993397235870361},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5890567302703857},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5114613771438599},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.510592520236969},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4897747039794922},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.46565109491348267},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45644786953926086},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4246925115585327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0973055362701416},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10458-021-09527-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-021-09527-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-021-09527-5.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10458-021-09527-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-021-09527-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-021-09527-5.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3195099242.pdf","grobid_xml":"https://content.openalex.org/works/W3195099242.grobid-xml"},"referenced_works_count":114,"referenced_works":["https://openalex.org/W2337330","https://openalex.org/W567721252","https://openalex.org/W779494576","https://openalex.org/W1581407678","https://openalex.org/W1591713425","https://openalex.org/W1594201624","https://openalex.org/W1969685488","https://openalex.org/W1971890413","https://openalex.org/W1986014385","https://openalex.org/W1988526405","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2101524054","https://openalex.org/W2116671302","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2161800642","https://openalex.org/W2166302491","https://openalex.org/W2167224731","https://openalex.org/W2169106844","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2417786368","https://openalex.org/W2419612459","https://openalex.org/W2434014514","https://openalex.org/W2561776174","https://openalex.org/W2563829177","https://openalex.org/W2594640072","https://openalex.org/W2596982695","https://openalex.org/W2604338815","https://openalex.org/W2604763608","https://openalex.org/W2614839826","https://openalex.org/W2616430965","https://openalex.org/W2626804490","https://openalex.org/W2733961795","https://openalex.org/W2736629007","https://openalex.org/W2737215407","https://openalex.org/W2739573821","https://openalex.org/W2741122588","https://openalex.org/W2744921630","https://openalex.org/W2755546070","https://openalex.org/W2785324569","https://openalex.org/W2786800733","https://openalex.org/W2786917922","https://openalex.org/W2788741142","https://openalex.org/W2788862220","https://openalex.org/W2803616302","https://openalex.org/W2810041204","https://openalex.org/W2823112946","https://openalex.org/W2883899184","https://openalex.org/W2886012730","https://openalex.org/W2889659926","https://openalex.org/W2895453875","https://openalex.org/W2895558617","https://openalex.org/W2899205164","https://openalex.org/W2903242674","https://openalex.org/W2904453761","https://openalex.org/W2921829327","https://openalex.org/W2922007426","https://openalex.org/W2950229905","https://openalex.org/W2950735232","https://openalex.org/W2951158797","https://openalex.org/W2951262671","https://openalex.org/W2951775809","https://openalex.org/W2952991114","https://openalex.org/W2962943921","https://openalex.org/W2963094133","https://openalex.org/W2963099939","https://openalex.org/W2963359646","https://openalex.org/W2963376229","https://openalex.org/W2963489214","https://openalex.org/W2963523627","https://openalex.org/W2963704132","https://openalex.org/W2964059111","https://openalex.org/W2964161785","https://openalex.org/W2964273112","https://openalex.org/W2964327384","https://openalex.org/W2971196730","https://openalex.org/W2979211489","https://openalex.org/W2980225636","https://openalex.org/W2982041329","https://openalex.org/W2982852993","https://openalex.org/W2990138404","https://openalex.org/W2994847258","https://openalex.org/W2995453501","https://openalex.org/W2995551516","https://openalex.org/W2999385649","https://openalex.org/W2999714443","https://openalex.org/W3046288827","https://openalex.org/W3092203123","https://openalex.org/W3098664323","https://openalex.org/W3099324303","https://openalex.org/W3110718495","https://openalex.org/W3136796994","https://openalex.org/W4246078117","https://openalex.org/W6600099587","https://openalex.org/W6616173779","https://openalex.org/W6634906388","https://openalex.org/W6635701881","https://openalex.org/W6682849425","https://openalex.org/W6684025599","https://openalex.org/W6718092244","https://openalex.org/W6730844258","https://openalex.org/W6735944222","https://openalex.org/W6736021936","https://openalex.org/W6740801417","https://openalex.org/W6748208641","https://openalex.org/W6751285671","https://openalex.org/W6753060773","https://openalex.org/W6754957883","https://openalex.org/W6756303580","https://openalex.org/W6765008394","https://openalex.org/W6767572230"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"reinforcement":[2],"learning":[3,50,82,118,187],"methods":[4],"have":[5],"achieved":[6],"significant":[7],"successes":[8],"in":[9,81,134,189,194],"complex":[10],"decision-making":[11],"problems.":[12],"In":[13,97],"fact,":[14],"they":[15],"traditionally":[16],"rely":[17],"on":[18,168],"well-designed":[19],"extrinsic":[20],"rewards,":[21],"which":[22],"limits":[23],"their":[24],"applicability":[25],"to":[26,46,61,84,114,129],"many":[27],"real-world":[28],"tasks":[29,193],"where":[30,153],"rewards":[31],"are":[32,79],"naturally":[33],"sparse.":[34],"While":[35],"cloning":[36],"behaviors":[37],"provided":[38],"by":[39],"an":[40],"expert":[41,158],"is":[42,162],"a":[43,52,86,102,146,169],"promising":[44],"approach":[45],"the":[47,69,74,92,117,123,131,140,154,157,160,175,192],"exploration":[48,197],"problem,":[49],"from":[51,73,91,174],"fixed":[53],"set":[54,94],"of":[55,63,89,95,111,125,139,151,171,191,196],"demonstrations":[56,113,128],"may":[57],"be":[58],"impracticable":[59],"due":[60],"lack":[62],"state":[64,141],"coverage":[65],"or":[66],"distribution":[67],"mismatch\u2014when":[68],"learner\u2019s":[70],"goal":[71],"deviates":[72],"demonstrated":[75],"behaviors.":[76],"Besides,":[77],"we":[78,100,121],"interested":[80],"how":[83],"reach":[85],"wide":[87],"range":[88],"goals":[90,152],"same":[93],"demonstrations.":[96],"this":[98],"work":[99],"propose":[101],"novel":[103],"goal-conditioned":[104],"method":[105,167,183],"that":[106,181],"leverages":[107],"very":[108],"small":[109],"sets":[110],"goal-driven":[112,127],"massively":[115],"accelerate":[116],"process.":[119],"Crucially,":[120],"introduce":[122],"concept":[124],"active":[126],"query":[130],"demonstrator":[132],"only":[133],"hard-to-learn":[135],"and":[136,159,199],"uncertain":[137],"regions":[138],"space.":[142],"We":[143,164],"further":[144],"present":[145],"strategy":[147],"for":[148],"prioritizing":[149],"sampling":[150],"disagreement":[155],"between":[156],"policy":[161],"maximized.":[163],"evaluate":[165],"our":[166,182],"variety":[170],"benchmark":[172],"environments":[173],"Mujoco":[176],"domain.":[177],"Experimental":[178],"results":[179],"show":[180],"outperforms":[184],"prior":[185],"imitation":[186],"approaches":[188],"most":[190],"terms":[195],"efficiency":[198],"average":[200],"scores.":[201]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}