{"id":"https://openalex.org/W2799536307","doi":"https://doi.org/10.24963/ijcai.2018/650","title":"Planning and Learning with Stochastic Action Sets","display_name":"Planning and Learning with Stochastic Action Sets","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2799536307","doi":"https://doi.org/10.24963/ijcai.2018/650","mag":"2799536307"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/650","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/650","pdf_url":"https://www.ijcai.org/proceedings/2018/0650.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0650.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036934218","display_name":"Craig Boutilier","orcid":"https://orcid.org/0000-0001-9330-4545"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig Boutilier","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108816455","display_name":"Alon Cohen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alon Cohen","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089579452","display_name":"Avinatan Hassidim","orcid":"https://orcid.org/0000-0002-3855-344X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avinatan Hassidim","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014637159","display_name":"Yishay Mansour","orcid":"https://orcid.org/0000-0001-6891-2645"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yishay Mansour","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011166928","display_name":"Ofer Meshi","orcid":"https://orcid.org/0009-0005-3418-8771"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ofer Meshi","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045775773","display_name":"Martin Mladenov","orcid":"https://orcid.org/0009-0007-5565-5126"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Mladenov","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010575626","display_name":"Dale Schuurmans","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dale Schuurmans","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.3393,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.58604989,"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":"4674","last_page":"4682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10142","display_name":"Formal Methods in Verification","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9940000176429749,"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":0.8098664283752441},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6969937682151794},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6237813830375671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.614905834197998},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6066174507141113},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5688064694404602},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5517789125442505},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.5342812538146973},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.48348885774612427},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.46494096517562866},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43494993448257446},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42727911472320557},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.41919535398483276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3945269286632538},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31096774339675903},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2878808379173279},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23693758249282837}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8098664283752441},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6969937682151794},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6237813830375671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614905834197998},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6066174507141113},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5688064694404602},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5517789125442505},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.5342812538146973},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.48348885774612427},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.46494096517562866},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43494993448257446},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42727911472320557},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.41919535398483276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3945269286632538},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31096774339675903},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2878808379173279},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23693758249282837},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2018/650","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/650","pdf_url":"https://www.ijcai.org/proceedings/2018/0650.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.02363","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.02363","pdf_url":"https://arxiv.org/pdf/1805.02363","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:2799536307","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1805.02363","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.1805.02363","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.02363","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:10.24963/ijcai.2018/650","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/650","pdf_url":"https://www.ijcai.org/proceedings/2018/0650.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2799536307.pdf","grobid_xml":"https://content.openalex.org/works/W2799536307.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1763335505","https://openalex.org/W1956354821","https://openalex.org/W1974714155","https://openalex.org/W2008098735","https://openalex.org/W2039114216","https://openalex.org/W2090502364","https://openalex.org/W2100440346","https://openalex.org/W2104921433","https://openalex.org/W2108234048","https://openalex.org/W2119567691","https://openalex.org/W2121136483","https://openalex.org/W2141076336","https://openalex.org/W2142620093","https://openalex.org/W2145339207","https://openalex.org/W2155640779","https://openalex.org/W2275802500","https://openalex.org/W2742154030"],"related_works":["https://openalex.org/W2997053847","https://openalex.org/W1548889916","https://openalex.org/W2546801625","https://openalex.org/W1024197927","https://openalex.org/W2154623234","https://openalex.org/W2942369252","https://openalex.org/W2945129946","https://openalex.org/W1654728867","https://openalex.org/W2808013820","https://openalex.org/W2898656812","https://openalex.org/W2497373367","https://openalex.org/W3041453306","https://openalex.org/W2264110120","https://openalex.org/W1968653071","https://openalex.org/W2495570292","https://openalex.org/W2200122131","https://openalex.org/W1593140824","https://openalex.org/W176737593","https://openalex.org/W37272079","https://openalex.org/W307767029"],"abstract_inverted_index":{"In":[0,41,91],"many":[1],"practical":[2],"uses":[3],"of":[4,10],"reinforcement":[5],"learning":[6],"(RL)":[7],"the":[8,31,134],"set":[9],"actions":[11,102],"available":[12,104],"at":[13],"a":[14,18,70,74,109,128],"given":[15],"state":[16],"is":[17,89],"random":[19],"variable,":[20],"with":[21,49,85,105],"realizations":[22],"governed":[23],"by":[24],"an":[25,78],"exogenous":[26],"stochastic":[27,50],"process.":[28],"Somewhat":[29],"surprisingly,":[30],"foundations":[32],"for":[33,112,123,133],"such":[34],"sequential":[35],"decision":[36],"processes":[37],"have":[38,69],"been":[39],"unaddressed.":[40],"this":[42,67],"work,":[43],"we":[44,81,94],"formalize":[45],"and":[46,63,108,119,126],"investigate":[47],"MDPs":[48],"action":[51,87],"sets":[52,88],"(SAS-MDPs)":[53],"to":[54],"provide":[55,127],"these":[56],"foundations.":[57],"We":[58,115],"show":[59,82],"that":[60,72,83],"optimal":[61],"policies":[62],"value":[64,118],"functions":[65],"in":[66],"model":[68,111],"structure":[71],"admits":[73],"compact":[75],"representation.":[76],"From":[77],"RL":[79],"perspective,":[80],"Q-learning":[84],"sampled":[86],"sound.":[90],"model-based":[92],"settings,":[93],"consider":[95],"two":[96],"important":[97],"special":[98],"cases:":[99],"when":[100],"individual":[101],"are":[103],"independent":[106],"probabilities,":[107],"sampling-based":[110],"unknown":[113],"distributions.":[114],"develop":[116],"polynomial-time":[117,129],"policy":[120],"iteration":[121],"methods":[122],"both":[124],"cases,":[125],"linear":[130],"programming":[131],"solution":[132],"first":[135],"case.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}