{"id":"https://openalex.org/W4315488616","doi":"https://doi.org/10.1109/cdc51059.2022.9992504","title":"Polya Decision Processes: A New History-Dependent Framework for Reinforcement Learning","display_name":"Polya Decision Processes: A New History-Dependent Framework for Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315488616","doi":"https://doi.org/10.1109/cdc51059.2022.9992504"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992504","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992504","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088294917","display_name":"Masahiro Kohjima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masahiro Kohjima","raw_affiliation_strings":["NTT Corporation,NTT Human Informatics Laboratories,Yokosuka,Japan,Kanagawa 239-0847"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Human Informatics Laboratories,Yokosuka,Japan,Kanagawa 239-0847","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088294917"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18874998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"4884","last_page":"4891"},"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9958999752998352,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9934999942779541,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9031358957290649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.692277193069458},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6796329617500305},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5988243222236633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5484011769294739},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5110620260238647},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5004158020019531},{"id":"https://openalex.org/keywords/decision-theory","display_name":"Decision theory","score":0.4627637267112732},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35595110058784485},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34823787212371826},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3410869836807251},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2317715883255005},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.13437646627426147},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07245472073554993}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9031358957290649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692277193069458},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6796329617500305},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5988243222236633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5484011769294739},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5110620260238647},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5004158020019531},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.4627637267112732},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35595110058784485},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34823787212371826},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3410869836807251},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2317715883255005},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.13437646627426147},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07245472073554993},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992504","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9992504","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1539216098","https://openalex.org/W1591195137","https://openalex.org/W1987794091","https://openalex.org/W2055921164","https://openalex.org/W2064675550","https://openalex.org/W2099768249","https://openalex.org/W2121092017","https://openalex.org/W2123651102","https://openalex.org/W2140188249","https://openalex.org/W2145339207","https://openalex.org/W2146398222","https://openalex.org/W2158282517","https://openalex.org/W2331759129","https://openalex.org/W2438667436","https://openalex.org/W2605260313","https://openalex.org/W2761873684","https://openalex.org/W3012712555","https://openalex.org/W3021208093","https://openalex.org/W3022566517","https://openalex.org/W4298023569","https://openalex.org/W4299570260","https://openalex.org/W6605390924","https://openalex.org/W6631864160","https://openalex.org/W6653228414","https://openalex.org/W6677939520","https://openalex.org/W6678409309","https://openalex.org/W6681781451","https://openalex.org/W6683084483","https://openalex.org/W6683363733","https://openalex.org/W6692405165","https://openalex.org/W6776438516"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"We":[0,26,48],"propose":[1],"a":[2,34],"new":[3,35],"framework":[4],"for":[5,59],"sequential":[6],"decision":[7],"making,":[8],"Polya":[9,23],"Decision":[10],"Processes":[11],"(PDP);":[12],"it":[13],"can":[14,30],"express":[15],"the":[16,22,62],"agent\u2019s":[17],"history-dependent":[18],"transitions":[19],"by":[20,70],"using":[21,61],"urn":[24,45],"model.":[25],"show":[27],"that":[28],"PDP":[29,60],"be":[31],"converted":[32],"into":[33],"type":[36],"of":[37],"Belief-MDP,":[38],"whose":[39],"belief":[40,63],"update":[41],"equation":[42],"requires":[43],"only":[44],"model":[46],"parameters.":[47],"introduce":[49],"its":[50],"theory,":[51],"value":[52],"iteration":[53],"algorithm,":[54],"and":[55],"reinforcement":[56],"learning":[57],"algorithm":[58],"state":[64],"representation.":[65],"Their":[66],"effectiveness":[67],"is":[68],"confirmed":[69],"numerical":[71],"experiments.":[72]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}