{"id":"https://openalex.org/W2903348269","doi":"https://doi.org/10.1609/aaai.v33i01.33015175","title":"Natural Option Critic","display_name":"Natural Option Critic","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2903348269","doi":"https://doi.org/10.1609/aaai.v33i01.33015175","mag":"2903348269"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33015175","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015175","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33015175","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032025273","display_name":"Saket Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saket Tiwari","raw_affiliation_strings":["University of Massachusetts Amherst","University of Massachusetts, Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066332280","display_name":"Philip S. Thomas","orcid":"https://orcid.org/0000-0002-9904-1800"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Thomas","raw_affiliation_strings":["University of Massachusetts Amherst","University of Massachusetts, Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00596306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"5175","last_page":"5182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9902999997138977,"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":0.9902999997138977,"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":0.9603000283241272,"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/parameterized-complexity","display_name":"Parameterized complexity","score":0.9125714302062988},{"id":"https://openalex.org/keywords/fisher-information","display_name":"Fisher information","score":0.6559444665908813},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5975943207740784},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5254793763160706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5241620540618896},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.488665372133255},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46514996886253357},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.453507661819458},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41241806745529175},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3957251310348511},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24633485078811646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14988234639167786},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07628914713859558}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.9125714302062988},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.6559444665908813},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5975943207740784},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5254793763160706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5241620540618896},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.488665372133255},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46514996886253357},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.453507661819458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41241806745529175},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3957251310348511},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24633485078811646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14988234639167786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07628914713859558},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v33i01.33015175","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015175","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1812.01488","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.01488","pdf_url":"https://arxiv.org/pdf/1812.01488","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"mag:2903348269","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1812.01488.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1812.01488","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1812.01488","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33015175","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015175","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1479979375","https://openalex.org/W2024390895","https://openalex.org/W2108535023","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2136602922","https://openalex.org/W2144647101","https://openalex.org/W2155027007","https://openalex.org/W2155894447","https://openalex.org/W2260756217","https://openalex.org/W2592215206","https://openalex.org/W2695227890","https://openalex.org/W2739741052","https://openalex.org/W2952509347","https://openalex.org/W6608133726","https://openalex.org/W6631122705","https://openalex.org/W6633472939","https://openalex.org/W6637967152","https://openalex.org/W6639024717","https://openalex.org/W6642904842","https://openalex.org/W6674268137","https://openalex.org/W6676772908","https://openalex.org/W6677049199","https://openalex.org/W6679257226","https://openalex.org/W6679590010","https://openalex.org/W6682998330","https://openalex.org/W6683195989","https://openalex.org/W6683443546","https://openalex.org/W6683993359","https://openalex.org/W6719767544","https://openalex.org/W6722065765","https://openalex.org/W6727349600","https://openalex.org/W6739451694"],"related_works":["https://openalex.org/W2963011537","https://openalex.org/W1604225666","https://openalex.org/W1000080145","https://openalex.org/W1534640128","https://openalex.org/W2613714061","https://openalex.org/W2934915631","https://openalex.org/W2981772821","https://openalex.org/W3124240834","https://openalex.org/W2102288976","https://openalex.org/W3121745736","https://openalex.org/W1598494920","https://openalex.org/W1509499988","https://openalex.org/W3123899507","https://openalex.org/W1599680403","https://openalex.org/W2766031037","https://openalex.org/W2946482304","https://openalex.org/W3122732203","https://openalex.org/W3123653445","https://openalex.org/W1984396721","https://openalex.org/W2751743787"],"abstract_inverted_index":{"The":[0],"recently":[1],"proposed":[2],"option-critic":[3,56],"architecture":[4,57],"(Bacon,":[5],"Harb,":[6],"and":[7,125,146,156],"Precup":[8],"2017)":[9],"provides":[10,22],"a":[11,23,40,129],"stochastic":[12],"policy":[13,145],"gradient":[14,28,65,94,139,186],"approach":[15,133],"to":[16,25,36,61,136,169],"hierarchical":[17],"reinforcement":[18],"learning.":[19],"Specifically,":[20],"it":[21],"way":[24],"estimate":[26,62],"the":[27,30,55,63,69,76,89,92,101,114,143,161,174,184],"of":[29,43,68,91,150,164],"expected":[31,70],"discounted":[32,71],"return":[33],"with":[34,106,119,153],"respect":[35],"parameters":[37],"that":[38,79],"define":[39],"finite":[41],"number":[42,163],"temporally":[44],"extended":[45,60],"actions,":[46],"called":[47],"options.":[48],"In":[49],"this":[50,74,83,96],"paper":[51,84],"we":[52,80,172],"show":[53],"how":[54,127],"can":[58,128],"be":[59,134],"natural":[64,93,138,175],"(Amari":[66],"1998)":[67],"return.":[72],"To":[73],"end,":[75],"central":[77],"questions":[78,171],"consider":[81],"in":[82,95,160],"are:":[85],"1)":[86],"what":[87,99,112],"is":[88,100,113],"definition":[90],"context,":[97],"2)":[98],"Fisher":[102,115],"information":[103,116],"matrix":[104,117],"associated":[105,118],"an":[107,120,151],"option\u2019s":[108,121],"parameterized":[109,122,144,147],"policy,":[110],"3)":[111],"termination":[123,148],"function,":[124],"4)":[126],"compatible":[130],"function":[131],"approximation":[132],"leveraged":[135],"obtain":[137],"estimates":[140],"for":[141],"both":[142],"functions":[149],"option":[152,176],"per-time-step":[154],"time":[155],"space":[157],"complexity":[158],"linear":[159],"total":[162],"parameters.":[165],"Based":[166],"on":[167],"answers":[168],"these":[170],"introduce":[173],"critic":[177],"algorithm.":[178],"Experimental":[179],"results":[180],"showcase":[181],"improvement":[182],"over":[183],"vanilla":[185],"approach.":[187]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}