{"id":"https://openalex.org/W2964399043","doi":"https://doi.org/10.24963/ijcai.2019/270","title":"The Expected-Length Model of Options","display_name":"The Expected-Length Model of Options","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964399043","doi":"https://doi.org/10.24963/ijcai.2019/270","mag":"2964399043"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/270","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/270","pdf_url":"https://www.ijcai.org/proceedings/2019/0270.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0270.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080191195","display_name":"David Abel","orcid":"https://orcid.org/0000-0001-6311-9007"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Abel","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012600744","display_name":"John Winder","orcid":null},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Winder","raw_affiliation_strings":["University of Maryland, Baltimore County"],"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111990167","display_name":"Marie desJardins","orcid":null},"institutions":[{"id":"https://openalex.org/I179245896","display_name":"Simmons University","ror":"https://ror.org/04mbfgm16","country_code":"US","type":"education","lineage":["https://openalex.org/I179245896"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marie desJardins","raw_affiliation_strings":["Simmons University"],"affiliations":[{"raw_affiliation_string":"Simmons University","institution_ids":["https://openalex.org/I179245896"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Littman","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080191195"],"corresponding_institution_ids":["https://openalex.org/I175594653"],"apc_list":null,"apc_paid":null,"fwci":0.4335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71729951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1951","last_page":"1958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"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":0.9961000084877014,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7184491157531738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6734955906867981},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.6158795952796936},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6068547964096069},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5224608182907104},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4685198962688446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3401058316230774},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23341700434684753},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22911974787712097},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08821648359298706}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7184491157531738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6734955906867981},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6158795952796936},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6068547964096069},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5224608182907104},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4685198962688446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3401058316230774},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23341700434684753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22911974787712097},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08821648359298706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/270","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/270","pdf_url":"https://www.ijcai.org/proceedings/2019/0270.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/270","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/270","pdf_url":"https://www.ijcai.org/proceedings/2019/0270.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7958170488","display_name":null,"funder_award_id":"D15AP00102","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8066592276","display_name":null,"funder_award_id":"IIS-1426452","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G89395400","display_name":"NRI: Collaborative Research: Jointly Learning Language and Affordances","funder_award_id":"1426452","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964399043.pdf","grobid_xml":"https://content.openalex.org/works/W2964399043.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W166185004","https://openalex.org/W1492014007","https://openalex.org/W1568042657","https://openalex.org/W1626977535","https://openalex.org/W1968768508","https://openalex.org/W2100677568","https://openalex.org/W2108535023","https://openalex.org/W2109910161","https://openalex.org/W2119567691","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2130535800","https://openalex.org/W2133458291","https://openalex.org/W2139612737","https://openalex.org/W2147558615","https://openalex.org/W2155640779","https://openalex.org/W2156067405","https://openalex.org/W2161966552","https://openalex.org/W2167590754","https://openalex.org/W2169977622","https://openalex.org/W2267881773","https://openalex.org/W2282350268","https://openalex.org/W2489939061","https://openalex.org/W2523728418","https://openalex.org/W2572640103","https://openalex.org/W2600491083","https://openalex.org/W2730602911","https://openalex.org/W2758731390","https://openalex.org/W2787066086","https://openalex.org/W2797811993","https://openalex.org/W2949773717","https://openalex.org/W2950040888","https://openalex.org/W2963134677","https://openalex.org/W2963394426","https://openalex.org/W2964227312","https://openalex.org/W3041202696","https://openalex.org/W4285719527","https://openalex.org/W4294336468","https://openalex.org/W4298023569"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Effective":[0],"options":[1,151],"can":[2],"make":[3],"reinforcement":[4],"learning":[5,26],"easier":[6],"by":[7,103],"enhancing":[8],"an":[9,27,31,54],"agent's":[10],"ability":[11],"to":[12,99,144],"both":[13],"explore":[14,114],"in":[15,34,85,154],"a":[16,38,64,75,92,132,155],"targeted":[17],"manner":[18],"and":[19,46,105],"plan":[20],"further":[21,82],"into":[22],"the":[23,48,68,100,115,127],"future.":[24],"However,":[25],"appropriate":[28],"model":[29,56,121],"of":[30,67,109,118],"option's":[32],"dynamics":[33],"hard,":[35],"requiring":[36],"estimating":[37],"highly":[39],"parameterized":[40],"probability":[41],"distribution.":[42],"This":[43],"paper":[44],"introduces":[45],"motivates":[47],"Expected-Length":[49],"Model":[50,71],"(ELM)":[51],"for":[52,57,126,135],"options,":[53],"alternate":[55],"transition":[58],"dynamics.":[59],"We":[60,81,113],"prove":[61,83],"ELM":[62,90,130,142],"is":[63,96,106,131],"(biased)":[65],"estimator":[66],"traditional":[69],"Multi-Time":[70],"(MTM),":[72],"but":[73],"provide":[74],"non-vacuous":[76],"bound":[77],"on":[78],"their":[79],"deviation.":[80],"that,":[84],"stochastic":[86],"shortest":[87],"path":[88],"problems,":[89],"induces":[91],"value":[93],"function":[94],"that":[95,129],"sufficiently":[97],"similar":[98],"one":[101],"induced":[102],"MTM,":[104],"thus":[107],"capable":[108],"supporting":[110],"near-optimal":[111],"behavior.":[112],"practical":[116],"utility":[117],"this":[119],"option":[120],"experimentally,":[122],"finding":[123],"consistent":[124],"support":[125],"thesis":[128],"suitable":[133],"replacement":[134],"MTM.":[136],"In":[137],"some":[138],"cases,":[139],"we":[140],"find":[141],"leads":[143],"more":[145],"sample":[146],"efficient":[147],"learning,":[148],"especially":[149],"when":[150],"are":[152],"arranged":[153],"hierarchy.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}