{"id":"https://openalex.org/W3148751076","doi":"https://doi.org/10.1109/icm46511.2021.9385636","title":"GBDT Modeling of Deep Reinforcement Learning Agents Using Distillation","display_name":"GBDT Modeling of Deep Reinforcement Learning Agents Using Distillation","publication_year":2021,"publication_date":"2021-03-07","ids":{"openalex":"https://openalex.org/W3148751076","doi":"https://doi.org/10.1109/icm46511.2021.9385636","mag":"3148751076"},"language":"en","primary_location":{"id":"doi:10.1109/icm46511.2021.9385636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icm46511.2021.9385636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Mechatronics (ICM)","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/A5091851375","display_name":"Toshiki Hatano","orcid":null},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Toshiki Hatano","raw_affiliation_strings":["Kanazawa University, Kanazawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000097788","display_name":"Toi Tsuneda","orcid":"https://orcid.org/0000-0003-1913-9179"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toi Tsuneda","raw_affiliation_strings":["Kanazawa University, Kanazawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101989123","display_name":"Yuta Suzuki","orcid":"https://orcid.org/0000-0002-0019-4832"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Suzuki","raw_affiliation_strings":["Kanazawa University, Kanazawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017498105","display_name":"Kuniyasu Imade","orcid":null},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kuniyasu Imade","raw_affiliation_strings":["Kanazawa University, Kanazawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029881941","display_name":"Kazuki Shesimo","orcid":null},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuki Shesimo","raw_affiliation_strings":["Kanazawa University, Kanazawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102728648","display_name":"Satoshi Yamane","orcid":"https://orcid.org/0000-0001-7883-4054"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Yamane","raw_affiliation_strings":["Kanazawa University, Kanazawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091851375"],"corresponding_institution_ids":["https://openalex.org/I10091056"],"apc_list":null,"apc_paid":null,"fwci":0.6798,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74701334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"8","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":0.996399998664856,"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":0.996399998664856,"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/T11601","display_name":"Neuroscience and Neural Engineering","score":0.902400016784668,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9018999934196472,"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":0.8941020965576172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7727278470993042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7167732119560242},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.597683310508728},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5805111527442932},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5536643862724304},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5099843740463257},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49573004245758057},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4602021872997284},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4221463203430176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0992661714553833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08197095990180969}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8941020965576172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727278470993042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7167732119560242},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.597683310508728},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5805111527442932},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5536643862724304},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5099843740463257},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49573004245758057},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4602021872997284},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4221463203430176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0992661714553833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08197095990180969},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icm46511.2021.9385636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icm46511.2021.9385636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Mechatronics (ICM)","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":6,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1821462560","https://openalex.org/W2145339207","https://openalex.org/W2295598076","https://openalex.org/W3102476541","https://openalex.org/W6637404493"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912","https://openalex.org/W2145821588"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,29,61,80,89,92,97,101,110,117],"field":[4],"of":[5,31,91,112],"deep":[6,32,66],"reinforcement":[7,33,67],"learning":[8,34,68],"has":[9,14],"been":[10],"developed,":[11],"and":[12,42,114],"it":[13,24,43],"become":[15],"possible":[16],"to":[17,27,46,50,59,87],"learn":[18],"complex":[19],"task":[20],"processing":[21,118],"automatically.":[22],"However,":[23],"is":[25,44,76],"difficult":[26,45],"verify":[28],"safety":[30],"methods":[35],"because":[36],"their":[37],"contents":[38],"are":[39],"not":[40],"clear,":[41],"find":[47],"a":[48,70,105],"way":[49],"improve":[51],"them.":[52],"Therefore,":[53],"in":[54,79],"this":[55],"study,":[56],"we":[57],"aimed":[58],"transform":[60],"solution":[62,98],"obtained":[63,93],"internally":[64],"by":[65,95,100],"into":[69,104],"GBDT":[71,106],"model":[72,94],"using":[73],"distillation,":[74],"which":[75,108],"commonly":[77],"used":[78],"imaging":[81],"field.":[82],"This":[83],"method":[84],"enables":[85],"us":[86],"confirm":[88],"validity":[90],"converting":[96],"represented":[99],"neural":[102],"network":[103],"model,":[107],"reduces":[109],"number":[111],"calculations":[113],"speeds":[115],"up":[116],"time.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}