{"id":"https://openalex.org/W2740174381","doi":"https://doi.org/10.24963/ijcai.2017/717","title":"Approximate Value Iteration with Temporally Extended Actions (Extended Abstract)","display_name":"Approximate Value Iteration with Temporally Extended Actions (Extended Abstract)","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740174381","doi":"https://doi.org/10.24963/ijcai.2017/717","mag":"2740174381"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/717","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/717","pdf_url":"https://www.ijcai.org/proceedings/2017/0717.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth 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/2017/0717.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006380946","display_name":"Timothy Mann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["GB","IL"],"is_corresponding":true,"raw_author_name":"Timothy A. Mann","raw_affiliation_strings":["DeepMind","The Technion, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"The Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["The Technion","The Technion, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"The Technion","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"The Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["McGill University","McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006380946"],"corresponding_institution_ids":["https://openalex.org/I174306211","https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.09189228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5035","last_page":"5039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9941999912261963,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.9818000197410583,"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/landmark","display_name":"Landmark","score":0.7446467280387878},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7348536252975464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6933823227882385},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6223219037055969},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.591431736946106},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.559215784072876},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5020115375518799},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.43230023980140686},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.41572141647338867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3257213830947876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22945547103881836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15819555521011353},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12336817383766174},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09781479835510254},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.06598460674285889}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.7446467280387878},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7348536252975464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933823227882385},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6223219037055969},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.591431736946106},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.559215784072876},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5020115375518799},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43230023980140686},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.41572141647338867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3257213830947876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22945547103881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15819555521011353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12336817383766174},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09781479835510254},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06598460674285889},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/717","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/717","pdf_url":"https://www.ijcai.org/proceedings/2017/0717.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/717","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/717","pdf_url":"https://www.ijcai.org/proceedings/2017/0717.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G1304196372","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G4825343050","display_name":null,"funder_award_id":"06638","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740174381.pdf","grobid_xml":"https://content.openalex.org/works/W2740174381.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W127341816","https://openalex.org/W1037351197","https://openalex.org/W1556824961","https://openalex.org/W1968768508","https://openalex.org/W2034567043","https://openalex.org/W2090170171","https://openalex.org/W2109910161","https://openalex.org/W2117355432","https://openalex.org/W2119567691","https://openalex.org/W2130535800","https://openalex.org/W2143435603","https://openalex.org/W2144032829","https://openalex.org/W2167590754","https://openalex.org/W2949773717","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2026924879","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W2052388267","https://openalex.org/W2950647290","https://openalex.org/W1968481813","https://openalex.org/W2807018115","https://openalex.org/W2051622126"],"abstract_inverted_index":{"The":[0],"options":[1,24,38,77,92,113,149,162],"framework":[2],"provides":[3],"a":[4,29,49,57,79,118,125],"concrete":[5],"way":[6],"to":[7,88],"implement":[8],"and":[9,78,101,143,150,157,174],"reason":[10],"about":[11],"temporally":[12],"extended":[13],"actions.":[14,46],"Existing":[15],"literature":[16],"has":[17],"demonstrated":[18],"the":[19,53,83,105,133,146,152],"value":[20,84,134],"of":[21,31,52,56,82,120],"planning":[22,36,43,115],"with":[23,37,44,69],"empirically,":[25],"but":[26],"there":[27],"is":[28,39],"lack":[30],"theoretical":[32,156],"analysis":[33,51,72],"formalizing":[34],"when":[35,97],"more":[40],"efficient":[41],"than":[42],"primitive":[45],"We":[47,140],"provide":[48],"general":[50],"convergence":[54,95],"rate":[55],"popular":[58],"Approximate":[59],"Value":[60,66],"Iteration":[61,67],"(AVI)":[62],"algorithm":[63],"called":[64],"Fitted":[65],"(FVI)":[68],"options.":[70],"Our":[71,155],"reveals":[73],"that":[74,131,161],"longer":[75],"duration":[76],"pessimistic":[80],"estimate":[81],"function":[85,135],"both":[86],"lead":[87],"faster":[89],"convergence.":[90,177],"Furthermore,":[91],"can":[93,163],"improve":[94],"even":[96],"they":[98],"are":[99],"suboptimal":[100],"sparsely":[102],"distributed":[103],"throughout":[104],"state":[106],"space.":[107],"Next":[108],"we":[109],"consider":[110],"generating":[111],"useful":[112],"for":[114],"based":[116],"on":[117],"subset":[119],"landmark":[121,138],"states.":[122,139],"This":[123],"suggests":[124],"new":[126],"algorithm,":[127],"Landmark-based":[128],"AVI":[129,169],"(LAVI),":[130],"represents":[132],"only":[136],"at":[137],"analyze":[141],"OFVI":[142],"LAVI":[144],"using":[145],"proposed":[147],"landmark-based":[148],"compare":[151],"two":[153],"algorithms.":[154],"experimental":[158],"results":[159],"demonstrate":[160],"play":[164],"an":[165],"important":[166],"role":[167],"in":[168],"by":[170],"decreasing":[171],"approximation":[172],"error":[173],"inducing":[175],"fast":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}