{"id":"https://openalex.org/W1515117609","doi":"https://doi.org/10.1109/iat.2004.1342918","title":"CHQ: a multi-agent reinforcement learning scheme for partially observable markov decision processes","display_name":"CHQ: a multi-agent reinforcement learning scheme for partially observable markov decision processes","publication_year":2004,"publication_date":"2004-11-08","ids":{"openalex":"https://openalex.org/W1515117609","doi":"https://doi.org/10.1109/iat.2004.1342918","mag":"1515117609"},"language":"en","primary_location":{"id":"doi:10.1109/iat.2004.1342918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iat.2004.1342918","pdf_url":null,"source":{"id":"https://openalex.org/S4363608984","display_name":"Proceedings. IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 2004. (IAT 2004).","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":"Proceedings. IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 2004. (IAT 2004).","raw_type":"proceedings-article"},"type":"article","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/A5018507838","display_name":"Hiroshi Osada","orcid":null},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"H. Osada","raw_affiliation_strings":["Department of Information Engineering, Graduate School of Engineering, Hiroshima University, Japan","Department of Information Engineering, Hiroshima University, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Graduate School of Engineering, Hiroshima University, Japan","institution_ids":["https://openalex.org/I113306721"]},{"raw_affiliation_string":"Department of Information Engineering, Hiroshima University, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087923932","display_name":"Satoshi Fujita","orcid":"https://orcid.org/0000-0001-9412-7309"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Fujita","raw_affiliation_strings":["Department of Information Engineering, Graduate School of Engineering, Hiroshima University, Japan","Department of Information Engineering, Hiroshima University, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Graduate School of Engineering, Hiroshima University, Japan","institution_ids":["https://openalex.org/I113306721"]},{"raw_affiliation_string":"Department of Information Engineering, Hiroshima University, Japan","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018507838"],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12419146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"bcs g2010 28","issue":null,"first_page":"17","last_page":"23"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9721999764442444,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9671000242233276,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.9627203941345215},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8713955879211426},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8599928617477417},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7730429172515869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6756101846694946},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5935614109039307},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5821247696876526},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5487412810325623},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5052374005317688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49793410301208496},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4670490324497223},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4652223587036133},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4001306891441345},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36811286211013794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3584611713886261},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16586396098136902},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06890231370925903}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9627203941345215},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8713955879211426},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8599928617477417},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7730429172515869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6756101846694946},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5935614109039307},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5821247696876526},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5487412810325623},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5052374005317688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49793410301208496},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4670490324497223},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4652223587036133},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4001306891441345},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36811286211013794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3584611713886261},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16586396098136902},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06890231370925903},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iat.2004.1342918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iat.2004.1342918","pdf_url":null,"source":{"id":"https://openalex.org/S4363608984","display_name":"Proceedings. IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 2004. (IAT 2004).","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":"Proceedings. IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 2004. (IAT 2004).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W96529184","https://openalex.org/W1557517019","https://openalex.org/W2013106993","https://openalex.org/W2098755476","https://openalex.org/W2121863487","https://openalex.org/W2144041366","https://openalex.org/W2912185451","https://openalex.org/W4214717370","https://openalex.org/W4242280782","https://openalex.org/W6603905768"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2364406457","https://openalex.org/W2173087131","https://openalex.org/W1997350370"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,37,42,66,107],"reinforcement":[3],"learning":[4],"scheme":[5,94],"called":[6],"CHQ":[7,53],"that":[8,25,68,103],"could":[9,70],"efficiently":[10],"acquire":[11,106],"appropriate":[12,83],"policies":[13],"under":[14,85],"partially":[15],"observable":[16],"Markov":[17],"decision":[18],"processes":[19],"(POMDP)":[20],"involving":[21],"probabilistic":[22,38,123],"state":[23,124],"transitions,":[24],"frequently":[26],"occurs":[27],"in":[28,31,64],"multiagent":[29],"systems":[30],"which":[32],"each":[33,86],"agent":[34],"independently":[35],"takes":[36],"action":[39],"based":[40],"on":[41],"partial":[43],"observation":[44],"of":[45,52,75,91,100],"the":[46,57,72,76,92,117],"underlying":[47],"environment.":[48],"A":[49],"key":[50],"idea":[51],"is":[54,95,120],"to":[55],"extend":[56],"HQ-learning":[58],"proposed":[59,93],"by":[60],"Wiering":[61],"et":[62],"al.":[63],"such":[65],"way":[67],"it":[69,104],"learn":[71],"activation":[73],"order":[74],"MDP":[77,87],"subtasks":[78],"as":[79,81],"well":[80],"an":[82],"policy":[84,109],"subtask.":[88],"The":[89,98],"quality":[90],"experimentally":[96],"evaluated.":[97],"result":[99],"experiments":[101],"implies":[102],"can":[105],"deterministic":[108],"with":[110,122],"sufficiently":[111],"high":[112],"success":[113],"rate,":[114],"even":[115],"if":[116],"given":[118],"task":[119],"POMDP":[121],"transitions.":[125]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}