{"id":"https://openalex.org/W2797886180","doi":"https://doi.org/10.1007/978-3-319-96145-3_36","title":"Value Iteration for Simple Stochastic Games: Stopping Criterion and Learning Algorithm","display_name":"Value Iteration for Simple Stochastic Games: Stopping Criterion and Learning Algorithm","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2797886180","doi":"https://doi.org/10.1007/978-3-319-96145-3_36","mag":"2797886180"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-96145-3_36","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-96145-3_36","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-319-96145-3_36","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Edon Kelmendi","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Edon Kelmendi","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Julia Kr\u00e4mer","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julia Kr\u00e4mer","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jan K\u0159et\u00ednsk\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan K\u0159et\u00ednsk\u00fd","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":null,"display_name":"Maximilian Weininger","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Weininger","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":14.1861,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.98861148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"623","last_page":"642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.27970001101493835,"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"}},"topics":[{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.27970001101493835,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.21819999814033508,"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/T11182","display_name":"Auction Theory and Applications","score":0.15530000627040863,"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/sequence","display_name":"Sequence (biology)","score":0.7649000287055969},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.7109000086784363},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6901999711990356},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5741999745368958},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.5666000247001648},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5630999803543091},{"id":"https://openalex.org/keywords/optimal-stopping","display_name":"Optimal stopping","score":0.5333999991416931},{"id":"https://openalex.org/keywords/stopping-time","display_name":"Stopping time","score":0.446399986743927}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7649000287055969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157999873161316},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7109000086784363},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6901999711990356},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.5666000247001648},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.539900004863739},{"id":"https://openalex.org/C99414536","wikidata":"https://www.wikidata.org/wiki/Q7098950","display_name":"Optimal stopping","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C99888217","wikidata":"https://www.wikidata.org/wiki/Q1288707","display_name":"Stopping time","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.35019999742507935},{"id":"https://openalex.org/C97542219","wikidata":"https://www.wikidata.org/wiki/Q497863","display_name":"SIMPLE algorithm","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C26955809","wikidata":"https://www.wikidata.org/wiki/Q10167591","display_name":"Initial value problem","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C5465570","wikidata":"https://www.wikidata.org/wiki/Q5326898","display_name":"Early stopping","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C2983961125","wikidata":"https://www.wikidata.org/wiki/Q1288707","display_name":"Stopping rule","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C141042865","wikidata":"https://www.wikidata.org/wiki/Q200125","display_name":"Expected value","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2669999897480011}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-319-96145-3_36","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-96145-3_36","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:1804.04901","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.04901","pdf_url":"https://arxiv.org/pdf/1804.04901","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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/978-3-319-96145-3_36","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-96145-3_36","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W127306328","https://openalex.org/W204760470","https://openalex.org/W1497161038","https://openalex.org/W1502195915","https://openalex.org/W1556387789","https://openalex.org/W1862398452","https://openalex.org/W1966347268","https://openalex.org/W1968136409","https://openalex.org/W1972203711","https://openalex.org/W2012151424","https://openalex.org/W2047901468","https://openalex.org/W2052092737","https://openalex.org/W2095304972","https://openalex.org/W2099618002","https://openalex.org/W2106272197","https://openalex.org/W2113113866","https://openalex.org/W2116708838","https://openalex.org/W2156268532","https://openalex.org/W2172183234","https://openalex.org/W2206317714","https://openalex.org/W2356671789","https://openalex.org/W2559829874","https://openalex.org/W2568766587","https://openalex.org/W2593267253","https://openalex.org/W2612788245","https://openalex.org/W2728937946","https://openalex.org/W2735021239","https://openalex.org/W2797886180","https://openalex.org/W2914135999","https://openalex.org/W2962990479","https://openalex.org/W4248784701"],"related_works":[],"abstract_inverted_index":{"Simple":[0],"stochastic":[1,61],"games":[2],"can":[3,106],"be":[4],"solved":[5],"by":[6,66],"value":[7,18,30,96],"iteration":[8],"(VI),":[9],"which":[10,113],"yields":[11,114],"a":[12,69,108],"sequence":[13,23,71],"of":[14,16,19,72,74,81,94],"under-approximations":[15],"the":[17,20,29,33,53,75,82,92,95,98,115,122],"game.":[21],"This":[22],"is":[24,39,64],"guaranteed":[25],"to":[26,28],"converge":[27],"only":[31],"in":[32],"limit.":[34],"Since":[35],"no":[36],"stopping":[37,55],"criterion":[38,56],"known,":[40],"this":[41],"technique":[42],"does":[43],"not":[44],"provide":[45,52,107],"any":[46],"guarantees":[47],"on":[48,59,78],"its":[49],"results.":[50],"We":[51],"first":[54],"for":[57],"VI":[58,86,111],"simple":[60],"games.":[62],"It":[63],"achieved":[65],"additionally":[67],"computing":[68],"convergent":[70],"over-approximations":[73],"value,":[76],"relying":[77],"an":[79,88],"analysis":[80],"game":[83,124],"graph.":[84,125],"Consequently,":[85],"becomes":[87],"anytime":[89],"algorithm":[90],"returning":[91],"approximation":[93],"and":[97],"current":[99],"error":[100],"bound.":[101],"As":[102],"another":[103],"consequence,":[104],"we":[105],"simulation-based":[109],"asynchronous":[110],"algorithm,":[112],"same":[116],"guarantees,":[117],"but":[118],"without":[119],"necessarily":[120],"exploring":[121],"whole":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-04-24T00:00:00"}