{"id":"https://openalex.org/W2947287204","doi":"https://doi.org/10.24963/ijcai.2019/357","title":"Conditions on Features for Temporal Difference-Like Methods to Converge","display_name":"Conditions on Features for Temporal Difference-Like Methods to Converge","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2947287204","doi":"https://doi.org/10.24963/ijcai.2019/357","mag":"2947287204"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/357","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/357","pdf_url":"https://www.ijcai.org/proceedings/2019/0357.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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0357.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073944062","display_name":"Marcus H\u00fctter","orcid":"https://orcid.org/0000-0002-3263-4097"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Marcus Hutter","raw_affiliation_strings":["Australian National University","AUSTRALIAN NATIONAL UNIVERSITY"],"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"AUSTRALIAN NATIONAL UNIVERSITY","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073288324","display_name":"Samuel Yang-Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Samuel Yang-Zhao","raw_affiliation_strings":["Australian National University","AUSTRALIAN NATIONAL UNIVERSITY"],"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"AUSTRALIAN NATIONAL UNIVERSITY","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088808464","display_name":"Sultan Javed Majeed","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sultan Javed Majeed","raw_affiliation_strings":["Australian National University","AUSTRALIAN NATIONAL UNIVERSITY"],"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"AUSTRALIAN NATIONAL UNIVERSITY","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073944062"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.04823464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2570","last_page":"2577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9961000084877014,"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":0.9916999936103821,"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/uniqueness","display_name":"Uniqueness","score":0.7968860268592834},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.682500958442688},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6444718241691589},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5440601110458374},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.5306274890899658},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5189177989959717},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4996936321258545},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4831806719303131},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4739297032356262},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4661617875099182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4497067332267761},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39370277523994446},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3646341860294342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18693125247955322},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07934805750846863}],"concepts":[{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.7968860268592834},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.682500958442688},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6444718241691589},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5440601110458374},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.5306274890899658},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5189177989959717},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4996936321258545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4831806719303131},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4739297032356262},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4661617875099182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4497067332267761},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39370277523994446},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3646341860294342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18693125247955322},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07934805750846863},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.24963/ijcai.2019/357","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/357","pdf_url":"https://www.ijcai.org/proceedings/2019/0357.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"},{"id":"pmh:oai:arXiv.org:1905.11702","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.11702","pdf_url":"https://arxiv.org/pdf/1905.11702","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":"","raw_type":"text"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/317431","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/317431","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019","raw_type":"Conference paper"},{"id":"doi:10.48550/arxiv.1905.11702","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.11702","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2947287204","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/357","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/357","pdf_url":"https://www.ijcai.org/proceedings/2019/0357.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947287204.pdf","grobid_xml":"https://content.openalex.org/works/W2947287204.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1547105496","https://openalex.org/W1547925194","https://openalex.org/W1646707810","https://openalex.org/W2075268401","https://openalex.org/W2098432798","https://openalex.org/W2121863487","https://openalex.org/W2125074935","https://openalex.org/W2139418546","https://openalex.org/W2169982856","https://openalex.org/W2305373430","https://openalex.org/W2473364827","https://openalex.org/W2951143668","https://openalex.org/W2964112359"],"related_works":["https://openalex.org/W2965291189","https://openalex.org/W2945624305","https://openalex.org/W2556181748","https://openalex.org/W2001029765","https://openalex.org/W2154058606","https://openalex.org/W2951651062","https://openalex.org/W2112525998","https://openalex.org/W2616752776","https://openalex.org/W2181316235","https://openalex.org/W88671919","https://openalex.org/W2885730995","https://openalex.org/W1510299683","https://openalex.org/W3214306075","https://openalex.org/W2154256239","https://openalex.org/W2909951968","https://openalex.org/W2496827972","https://openalex.org/W2885465588","https://openalex.org/W2322668629","https://openalex.org/W3092776912","https://openalex.org/W1867405698"],"abstract_inverted_index":{"The":[0],"convergence":[1,52,72],"of":[2,36,43,84,100],"many":[3,49],"reinforcement":[4,44],"learning":[5,45],"(RL)":[6],"algorithms":[7,111,137,177,186],"with":[8],"linear":[9],"function":[10,157],"approximation":[11,127],"has":[12],"been":[13],"investigated":[14],"extensively":[15],"but":[16],"most":[17,150],"proofs":[18],"assume":[19],"that":[20,67,109,135,167],"these":[21],"methods":[22],"converge":[23,112,144],"to":[24,51,113,143,145],"a":[25,33,40,54,62,81,101,130,172,181],"unique":[26],"solution.":[27],"In":[28],"this":[29,59],"paper,":[30],"we":[31,88,165],"provide":[32,180],"complete":[34],"characterization":[35],"non-uniqueness":[37,77],"issues":[38],"for":[39,149,175,183],"large":[41],"class":[42,83],"algorithms,":[46,91],"simultaneously":[47],"unifying":[48],"counter-examples":[50],"in":[53,125,139],"theoretical":[55],"framework.":[56],"We":[57,79],"achieve":[58],"by":[60],"proving":[61],"new":[63],"condition":[64,182],"on":[65],"features":[66,170],"can":[68,158],"determine":[69],"whether":[70],"the":[71,97,114,122,126,146,155],"assumptions":[73],"are":[74,94,171],"valid":[75],"or":[76],"holds.":[78],"consider":[80],"general":[82],"RL":[85],"methods,":[86],"which":[87],"call":[89],"natural":[90,110,136,176],"whose":[92],"solutions":[93],"characterized":[95],"as":[96],"fixed":[98],"point":[99],"projected":[102],"Bellman":[103],"equation.":[104],"Our":[105],"main":[106],"result":[107],"proves":[108],"correct":[115],"solution":[116,148],"if":[117,120,154],"and":[118,178],"only":[119],"all":[121],"value":[123,156],"functions":[124],"space":[128],"satisfy":[129],"certain":[131],"shape.":[132],"This":[133],"implies":[134],"are,":[138],"general,":[140],"inherently":[141],"prone":[142],"wrong":[147],"feature":[151,189],"choices":[152],"even":[153],"be":[159],"represented":[160],"exactly.":[161],"Given":[162],"our":[163],"results,":[164],"show":[166],"state":[168],"aggregation-based":[169],"safe":[173],"choice":[174],"also":[179],"finding":[184],"convergent":[185],"under":[187],"other":[188],"constructions.":[190]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}