{"id":"https://openalex.org/W3101160782","doi":"https://doi.org/10.1145/3514260","title":"Reusability and Transferability of Macro Actions for Reinforcement Learning","display_name":"Reusability and Transferability of Macro Actions for Reinforcement Learning","publication_year":2022,"publication_date":"2022-02-24","ids":{"openalex":"https://openalex.org/W3101160782","doi":"https://doi.org/10.1145/3514260","mag":"3101160782"},"language":"en","primary_location":{"id":"doi:10.1145/3514260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514260","pdf_url":null,"source":{"id":"https://openalex.org/S4210221532","display_name":"ACM Transactions on Evolutionary Learning and Optimization","issn_l":"2688-299X","issn":["2688-299X","2688-3007"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Evolutionary Learning and Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.01478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112346398","display_name":"Yi-Hsiang Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yi-Hsiang Chang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084774178","display_name":"Kuan-Yu Chang","orcid":"https://orcid.org/0000-0003-1120-2970"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Yu Chang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-1120-2970","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078096030","display_name":"Henry Kuo","orcid":"https://orcid.org/0000-0002-4667-4794"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Kuo","raw_affiliation_strings":["Harvard University, Cambridge, Massachusetts"],"raw_orcid":"https://orcid.org/0000-0002-4667-4794","affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, Massachusetts","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028600832","display_name":"Chun\u2010Yi Lee","orcid":"https://orcid.org/0000-0002-4680-4800"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Yi Lee","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-4680-4800","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112346398"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00282229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9865000247955322,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9768000245094299,"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/transferability","display_name":"Transferability","score":0.9049823880195618},{"id":"https://openalex.org/keywords/reusability","display_name":"Reusability","score":0.8720367550849915},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.7379648685455322},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7048617005348206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.613076388835907},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5018787384033203},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3928735554218292},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.35328567028045654},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2840697169303894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2479235827922821},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17240193486213684},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13104307651519775},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.06054547429084778}],"concepts":[{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.9049823880195618},{"id":"https://openalex.org/C137981799","wikidata":"https://www.wikidata.org/wiki/Q1369184","display_name":"Reusability","level":3,"score":0.8720367550849915},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.7379648685455322},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7048617005348206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.613076388835907},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5018787384033203},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3928735554218292},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35328567028045654},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2840697169303894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2479235827922821},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17240193486213684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13104307651519775},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.06054547429084778},{"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/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3514260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514260","pdf_url":null,"source":{"id":"https://openalex.org/S4210221532","display_name":"ACM Transactions on Evolutionary Learning and Optimization","issn_l":"2688-299X","issn":["2688-299X","2688-3007"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Evolutionary Learning and Optimization","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1908.01478","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.01478","pdf_url":"https://arxiv.org/pdf/1908.01478","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.01478","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.01478","pdf_url":"https://arxiv.org/pdf/1908.01478","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1507087299","https://openalex.org/W1757796397","https://openalex.org/W1914583973","https://openalex.org/W1981627423","https://openalex.org/W2097571405","https://openalex.org/W2101602574","https://openalex.org/W2109910161","https://openalex.org/W2110415190","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2157466031","https://openalex.org/W2160927913","https://openalex.org/W2163883965","https://openalex.org/W2294663333","https://openalex.org/W2401064609","https://openalex.org/W2419612459","https://openalex.org/W2428834750","https://openalex.org/W2470931098","https://openalex.org/W2492794003","https://openalex.org/W2596367596","https://openalex.org/W2736601468","https://openalex.org/W2778749116","https://openalex.org/W2793035934","https://openalex.org/W2885550588","https://openalex.org/W2913668833","https://openalex.org/W2924136311","https://openalex.org/W2963276097","https://openalex.org/W2964043796","https://openalex.org/W2964067469","https://openalex.org/W2982333832","https://openalex.org/W3103279638","https://openalex.org/W3103780890","https://openalex.org/W3141007506","https://openalex.org/W4214717370","https://openalex.org/W4233691971","https://openalex.org/W4295184135","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6718233198","https://openalex.org/W6741002519","https://openalex.org/W6753925943","https://openalex.org/W6756303580"],"related_works":["https://openalex.org/W4282938614","https://openalex.org/W2161221533","https://openalex.org/W2906929912","https://openalex.org/W2099755394","https://openalex.org/W2350686889","https://openalex.org/W1965839502","https://openalex.org/W2621742671","https://openalex.org/W4229699405","https://openalex.org/W2114764029","https://openalex.org/W3101160782"],"abstract_inverted_index":{"Conventional":[0],"reinforcement":[1],"learning":[2,43],"(RL)":[3],"typically":[4],"determines":[5],"an":[6,27],"appropriate":[7],"primitive":[8,25],"action":[9,85,111],"at":[10],"each":[11],"timestep.":[12],"However,":[13],"by":[14,95],"using":[15],"a":[16,22,37,83,109,140],"proper":[17],"macro":[18,58,74,84,110,131,155],"action,":[19],"defined":[20],"as":[21],"sequence":[23],"of":[24,69,73,142,148,152],"actions,":[26],"RL":[28,90,97,135],"agent":[29],"is":[30,52],"able":[31],"to":[32,36,50,144],"bypass":[33],"intermediate":[34],"states":[35],"farther":[38],"state":[39],"and":[40,71,150],"facilitate":[41],"its":[42],"procedure.":[44],"The":[45,76],"problem":[46],"we":[47,65,128],"would":[48],"like":[49],"investigate":[51],"what":[53],"associated":[54],"beneficial":[55],"properties":[56,68,147],"that":[57,82,108],"actions":[59,132],"may":[60],"possess.":[61],"In":[62,125],"this":[63],"article,":[64],"unveil":[66],"the":[67,102,146,153],"reusability":[70,79,149],"transferability":[72,105,151],"actions.":[75,156],"first":[77,129],"property,":[78],",":[80,106],"means":[81],"derived":[86,154],"along":[87,133],"with":[88,121,134],"one":[89],"method":[91,98],"can":[92,112],"be":[93,113],"reused":[94],"another":[96],"for":[99,115],"training,":[100],"while":[101],"second":[103],"one,":[104],"indicates":[107],"utilized":[114],"training":[116],"agents":[117],"in":[118],"similar":[119],"environments":[120],"different":[122],"reward":[123],"settings.":[124],"our":[126],"experiments,":[127],"derive":[130],"methods.":[136],"We":[137],"then":[138],"provide":[139],"set":[141],"analyses":[143],"reveal":[145]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2020-11-23T00:00:00"}
