{"id":"https://openalex.org/W4415428404","doi":"https://doi.org/10.3233/faia251045","title":"Distilling Reinforcement Learning into Single-Batch Datasets","display_name":"Distilling Reinforcement Learning into Single-Batch Datasets","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428404","doi":"https://doi.org/10.3233/faia251045"},"language":null,"primary_location":{"id":"doi:10.3233/faia251045","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251045","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251045","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010990661","display_name":"Connor Wilhelm","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Connor Wilhelm","raw_affiliation_strings":["Computer Science Department, Brigham Young University"],"raw_orcid":"https://orcid.org/0009-0002-3028-7711","affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064318273","display_name":"Dan Ventura","orcid":"https://orcid.org/0000-0002-3111-2238"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Ventura","raw_affiliation_strings":["Computer Science Department, Brigham Young University"],"raw_orcid":"https://orcid.org/0000-0002-3111-2238","affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010990661"],"corresponding_institution_ids":["https://openalex.org/I100005738"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4759187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.833899974822998,"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":0.833899974822998,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.789900004863739,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.7020000219345093,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8676999807357788},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5871000289916992},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5611000061035156},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5094000101089478},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5041000247001648},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.38999998569488525},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.38830000162124634},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.3822000026702881},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.34790000319480896}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8676999807357788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755299985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.741100013256073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6015999913215637},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.38999998569488525},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.34790000319480896},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2992566924","wikidata":"https://www.wikidata.org/wiki/Q499210","display_name":"Animal learning","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251045","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251045","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251045","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251045","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dataset":[0],"distillation":[1,43],"compresses":[2],"a":[3,7,67,88,102],"large":[4],"dataset":[5,10,17,27],"into":[6,54,82,126,141],"small":[8],"synthetic":[9,16,145],"such":[11],"that":[12,42],"learning":[13,19,52,57,69,78],"on":[14,20,24],"the":[15,21,25,106,142],"approximates":[18],"original.":[22],"Training":[23],"distilled":[26],"can":[28],"be":[29],"performed":[30],"in":[31],"as":[32,34],"little":[33],"one":[35,77],"step":[36],"of":[37,91,105],"gradient":[38],"descent.":[39],"We":[40,86,117],"demonstrate":[41,118,137],"is":[44],"generalizable":[45],"to":[46,65,75,100,121],"different":[47],"tasks":[48],"by":[49],"distilling":[50,138],"reinforcement":[51,68],"environments":[53,125],"one-batch":[55],"supervised":[56,128],"datasets.":[58],"This":[59],"demonstrates":[60],"not":[61],"only":[62],"distillation\u2019s":[63,119,131],"ability":[64,74,120],"compress":[66,122],"task":[70],"but":[71],"also":[72],"its":[73],"transform":[76],"modality":[79],"(reinforcement":[80],"learning)":[81],"another":[83],"(supervised":[84],"learning).":[85],"present":[87],"novel":[89],"extension":[90,104],"proximal":[92],"policy":[93],"optimization":[94],"for":[95],"meta-learning":[96],"and":[97,113,136],"use":[98],"it":[99],"distill":[101],"multi-dimensional":[103],"classic":[107],"cart-pole":[108],"problem,":[109],"all":[110],"MuJoCo":[111],"environments,":[112],"several":[114],"Atari":[115],"games.":[116],"complex":[123],"RL":[124],"one-step":[127],"learning,":[129],"explore":[130],"generalizability":[132],"across":[133],"agent":[134],"architectures,":[135],"an":[139],"environment":[140],"smallest":[143],"possible":[144],"dataset.":[146]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}