{"id":"https://openalex.org/W2090170171","doi":"https://doi.org/10.1145/1102351.1102454","title":"Identifying useful subgoals in reinforcement learning by local graph partitioning","display_name":"Identifying useful subgoals in reinforcement learning by local graph partitioning","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2090170171","doi":"https://doi.org/10.1145/1102351.1102454","mag":"2090170171"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://scholarworks.umass.edu/bitstreams/338b159d-9e99-4cd7-b183-f6db14cf81d1/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079000862","display_name":"\u00d6zg\u00fcr \u015eim\u015fek","orcid":"https://orcid.org/0000-0001-5449-0437"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"funder","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"\u00d6zg\u00fcr \u015eim\u015fek","raw_affiliation_strings":["University of Massachusetts, Amherst MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055698707","display_name":"Alicia P. Wolfe","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"funder","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alicia P. Wolfe","raw_affiliation_strings":["University of Massachusetts, Amherst MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"funder","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew G. Barto","raw_affiliation_strings":["University of Massachusetts, Amherst MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.521,"has_fulltext":false,"cited_by_count":245,"citation_normalized_percentile":{"value":0.986579,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"816","last_page":"823"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9996,"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":0.9996,"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":0.9974,"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/T10142","display_name":"Formal Methods in Verification","score":0.9798,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/scope","display_name":"Scope (computer science)","score":0.64255536}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7997383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75783026},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.64255536},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.60230875},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.54093975},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48280394},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.47857407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45516288},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42394355},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38769215},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34892803},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17047215},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12079641},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09850183},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09499726},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/19","pdf_url":"https://scholarworks.umass.edu/bitstreams/338b159d-9e99-4cd7-b183-f6db14cf81d1/download","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":["University of Massachusetts Amherst"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cgi/viewcontent.cgi?article=1006&context=cs_faculty_pubs","pdf_url":"https://scholarworks.umass.edu/cgi/viewcontent.cgi?article=1006&context=cs_faculty_pubs","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":["University of Massachusetts Amherst"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_barto/4","pdf_url":"https://works.bepress.com/andrew_barto/4/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":["University of Massachusetts Amherst"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/19","pdf_url":"https://scholarworks.umass.edu/bitstreams/338b159d-9e99-4cd7-b183-f6db14cf81d1/download","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":["University of Massachusetts Amherst"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":20,"referenced_works":["https://openalex.org/W1536990779","https://openalex.org/W1540462738","https://openalex.org/W1568042657","https://openalex.org/W1585861384","https://openalex.org/W1586944634","https://openalex.org/W1598052524","https://openalex.org/W1968768508","https://openalex.org/W1977545325","https://openalex.org/W2109910161","https://openalex.org/W2114451917","https://openalex.org/W2121517924","https://openalex.org/W2121947440","https://openalex.org/W2125531986","https://openalex.org/W2132603077","https://openalex.org/W2132714442","https://openalex.org/W2141559645","https://openalex.org/W2143435603","https://openalex.org/W2158548602","https://openalex.org/W2160808139","https://openalex.org/W2799061466"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W4297873223","https://openalex.org/W4241523039","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W3009457412","https://openalex.org/W2999580272","https://openalex.org/W2350784623","https://openalex.org/W2328553770","https://openalex.org/W2126211886"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"new":[3],"subgoal-based":[4],"method":[5,15,43],"for":[6],"automatically":[7],"creating":[8],"useful":[9],"skills":[10],"in":[11],"reinforcement":[12],"learning.":[13],"Our":[14],"identifies":[16],"subgoals":[17,52],"by":[18],"partitioning":[19],"local":[20,37],"state":[21,63],"transition":[22],"graphs---those":[23],"that":[24,55],"are":[25],"constructed":[26],"using":[27],"only":[28],"the":[29,34,49,62],"most":[30],"recent":[31],"experiences":[32],"of":[33,39,51,61],"agent.":[35],"The":[36],"scope":[38],"our":[40],"subgoal":[41],"discovery":[42],"allows":[44],"it":[45],"to":[46],"successfully":[47],"identify":[48],"type":[50],"we":[53],"seek---states":[54],"lie":[56],"between":[57],"two":[58],"densely-connected":[59],"regions":[60],"space":[64],"while":[65],"producing":[66],"an":[67],"algorithm":[68],"with":[69],"low":[70],"computational":[71],"cost.":[72]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2090170171","counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":31}],"updated_date":"2025-03-23T00:48:44.279004","created_date":"2016-06-24"}