{"id":"https://openalex.org/W4306179821","doi":"https://doi.org/10.1007/s10994-022-06242-4","title":"A taxonomy for similarity metrics between Markov decision processes","display_name":"A taxonomy for similarity metrics between Markov decision processes","publication_year":2022,"publication_date":"2022-10-14","ids":{"openalex":"https://openalex.org/W4306179821","doi":"https://doi.org/10.1007/s10994-022-06242-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-022-06242-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06242-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06242-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","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/s10994-022-06242-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100645872","display_name":"Javier Garc\u00eda","orcid":"https://orcid.org/0000-0002-5638-5240"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Garc\u00eda","raw_affiliation_strings":["Departamento de Electr\u00f3nica y Computaci\u00f3n, Universidad de Santiago de Compostela, Santiago de Compostela, Spain"],"raw_orcid":"https://orcid.org/0000-0002-5638-5240","affiliations":[{"raw_affiliation_string":"Departamento de Electr\u00f3nica y Computaci\u00f3n, Universidad de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051819167","display_name":"\u00c1lvaro Vis\u00fas","orcid":null},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00c1lvaro Vis\u00fas","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Universidad Carlos III de Madrid, Legan\u00e9s, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Universidad Carlos III de Madrid, Legan\u00e9s, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004703726","display_name":"Fernando Fern\u00e1ndez","orcid":"https://orcid.org/0000-0003-3801-6801"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fernando Fern\u00e1ndez","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Universidad Carlos III de Madrid, Legan\u00e9s, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Universidad Carlos III de Madrid, Legan\u00e9s, Spain","institution_ids":["https://openalex.org/I50357001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100645872"],"corresponding_institution_ids":["https://openalex.org/I200284239"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.929,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78437712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"111","issue":"11","first_page":"4217","last_page":"4247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9962999820709229,"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":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.7659019231796265},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6749165058135986},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6450100541114807},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6088119149208069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5915737152099609},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5604697465896606},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5217129588127136},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.47683754563331604},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.47220784425735474},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4477236866950989},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4274420142173767},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.42446231842041016},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07890042662620544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659019231796265},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6749165058135986},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6450100541114807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6088119149208069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5915737152099609},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5604697465896606},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5217129588127136},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.47683754563331604},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.47220784425735474},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4477236866950989},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4274420142173767},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.42446231842041016},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07890042662620544},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10994-022-06242-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06242-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06242-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:e-archivo.uc3m.es:10016/36990","is_oa":true,"landing_page_url":"http://hdl.handle.net/10016/36990","pdf_url":"https://e-archivo.uc3m.es/bitstreams/0aba6495-15da-4e01-a8a2-045ca5619eae/download","source":{"id":"https://openalex.org/S4306400817","display_name":"e-Archivo (Carlos III University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I50357001","host_organization_name":"Universidad Carlos III de Madrid","host_organization_lineage":["https://openalex.org/I50357001"],"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":"info:eu-repo/semantics/article"},{"id":"pmh:oai:minerva.usc.es:10347/29969","is_oa":true,"landing_page_url":"http://hdl.handle.net/10347/29969","pdf_url":null,"source":{"id":"https://openalex.org/S4306400376","display_name":"Repositorio institucional da Universidade de Santiago de Compostela (University of Santiago de Compostela)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200284239","host_organization_name":"Universidade de Santiago de Compostela","host_organization_lineage":["https://openalex.org/I200284239"],"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":"journal article"}],"best_oa_location":{"id":"doi:10.1007/s10994-022-06242-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06242-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06242-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G311042921","display_name":null,"funder_award_id":"EPUC3M17","funder_id":"https://openalex.org/F4320313831","funder_display_name":"Comunidad de Madrid"}],"funders":[{"id":"https://openalex.org/F4320307774","display_name":"JPMorgan Chase and Company","ror":"https://ror.org/01x3kkr08"},{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320323770","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210"},{"id":"https://openalex.org/F4320328802","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306179821.pdf","grobid_xml":"https://content.openalex.org/works/W4306179821.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W23576351","https://openalex.org/W41554520","https://openalex.org/W193076044","https://openalex.org/W755046805","https://openalex.org/W867213644","https://openalex.org/W1433129784","https://openalex.org/W1504915502","https://openalex.org/W1515897776","https://openalex.org/W1534331386","https://openalex.org/W1546944959","https://openalex.org/W1568835640","https://openalex.org/W1573527757","https://openalex.org/W1582256513","https://openalex.org/W1612195517","https://openalex.org/W1925875298","https://openalex.org/W1974043469","https://openalex.org/W1983681808","https://openalex.org/W1990600049","https://openalex.org/W2004030284","https://openalex.org/W2017779181","https://openalex.org/W2018629084","https://openalex.org/W2039797165","https://openalex.org/W2056584142","https://openalex.org/W2058735307","https://openalex.org/W2064127653","https://openalex.org/W2078727257","https://openalex.org/W2098723043","https://openalex.org/W2099587183","https://openalex.org/W2100495367","https://openalex.org/W2105960367","https://openalex.org/W2107726111","https://openalex.org/W2110292307","https://openalex.org/W2117831564","https://openalex.org/W2118022839","https://openalex.org/W2123995443","https://openalex.org/W2126385963","https://openalex.org/W2141559023","https://openalex.org/W2163808368","https://openalex.org/W2169771756","https://openalex.org/W2191938486","https://openalex.org/W2194869982","https://openalex.org/W2257979135","https://openalex.org/W2271262891","https://openalex.org/W2464736835","https://openalex.org/W2464793473","https://openalex.org/W2468354762","https://openalex.org/W2531554541","https://openalex.org/W2559655401","https://openalex.org/W2581240229","https://openalex.org/W2760355785","https://openalex.org/W2792645523","https://openalex.org/W2808217720","https://openalex.org/W2924907019","https://openalex.org/W2945961113","https://openalex.org/W2964848402","https://openalex.org/W2967623629","https://openalex.org/W2990138404","https://openalex.org/W2997101648","https://openalex.org/W3005639539","https://openalex.org/W3007992747","https://openalex.org/W3012544020","https://openalex.org/W3036185205","https://openalex.org/W3088310808","https://openalex.org/W3100625157","https://openalex.org/W3102206498","https://openalex.org/W3119486431","https://openalex.org/W3120778962","https://openalex.org/W3126466933","https://openalex.org/W3211479928","https://openalex.org/W4221146753","https://openalex.org/W4226445831","https://openalex.org/W4255421341","https://openalex.org/W4298723254","https://openalex.org/W6600989536","https://openalex.org/W6635516443","https://openalex.org/W6677916085","https://openalex.org/W6680753846","https://openalex.org/W6712173889","https://openalex.org/W6775686901","https://openalex.org/W7074002762"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"Abstract":[0],"Although":[1],"the":[2,35,39,43,62,89,104,111,116,124,130,134,161,165,173,201,220,230],"notion":[3],"of":[4,14,37,45,48,91,107,136,180,196,203,232],"task":[5,126],"similarity":[6,108,174,181,204],"is":[7,32,101,143,156],"potentially":[8],"interesting":[9],"in":[10,42,56,78,99],"a":[11,46,52,57,144,194],"wide":[12],"range":[13],"areas":[15],"such":[16,211],"as":[17,223,225],"curriculum":[18],"learning":[19,44,54,75,81,131],"or":[20,182],"automated":[21],"planning,":[22],"it":[23],"has":[24,76],"mostly":[25],"been":[26,187],"tied":[27],"to":[28,51,94,122,139,160,171,218],"transfer":[29,74,149],"learning.":[30],"Transfer":[31,98],"based":[33,102],"on":[34,103],"idea":[36],"reusing":[38],"knowledge":[40,118,155],"acquired":[41],"set":[47],"source":[49,65],"tasks":[50,66,112],"new":[53,233],"process":[55],"target":[58,63,125],"task,":[59],"assuming":[60],"that":[61],"and":[64,127,199],"are":[67,113,168],"close":[68],"enough":[69],".":[70],"In":[71,164,189],"recent":[72],"years,":[73],"succeeded":[77],"making":[79],"reinforcement":[80],"(RL)":[82],"algorithms":[83],"more":[84],"efficient":[85],"(e.g.,":[86],"by":[87],"reducing":[88],"number":[90],"samples":[92],"needed":[93],"achieve":[95],"(near-)optimal":[96],"performance).":[97],"RL":[100,150],"core":[105],"concept":[106],":":[109],"whenever":[110],"similar":[114],",":[115],"transferred":[117,157],"can":[119],"be":[120],"reused":[121],"solve":[123],"significantly":[128],"improve":[129],"performance.":[132],"Therefore,":[133],"selection":[135],"good":[137],"metrics":[138,170,198],"measure":[140,172],"these":[141,197],"similarities":[142],"critical":[145],"aspect":[146],"when":[147,153],"building":[148],"algorithms,":[151],"especially":[152],"this":[154,190,216],"from":[158],"simulation":[159],"real":[162],"world.":[163],"literature,":[166,222],"there":[167],"many":[169,178],"between":[175],"MDPs,":[176],"hence,":[177],"definitions":[179,202],"its":[183],"complement":[184],"distance":[185],"have":[186],"considered.":[188],"paper,":[191],"we":[192],"propose":[193],"categorization":[195],"analyze":[200],"proposed":[205],"so":[206],"far,":[207],"taking":[208],"into":[209],"account":[210],"categorization.":[212],"We":[213],"also":[214],"follow":[215],"taxonomy":[217],"survey":[219],"existing":[221],"well":[224],"suggesting":[226],"future":[227],"directions":[228],"for":[229],"construction":[231],"metrics.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}