{"id":"https://openalex.org/W2105590108","doi":null,"title":"Learning Automata based Algorithms for Finding Optimal Policies in Fully Cooperative Markov Games","display_name":"Learning Automata based Algorithms for Finding Optimal Policies in Fully Cooperative Markov Games","alternate_titles":[],"publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2105590108","mag":"2105590108"},"language":"pl","primary_location":{"id":"mag:2105590108","doi":null,"is_oa":false,"landing_page_url":"http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.baztech-article-BPOK-0039-0066","pdf_url":null,"source":{"id":"https://openalex.org/S197975706","display_name":"PRZEGL\u0104D ELEKTROTECHNICZNY","issn_l":"0033-2097","issn":["0033-2097","2449-9544"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["erih-plus","norway-1","poland-70","russia-white-list-4"],"host_organization":"https://openalex.org/P4310317252","host_organization_name":"Stowarzyszenie Elektryk\u00f3w Polskich","host_organization_lineage":["https://openalex.org/P4310317252"],"host_organization_lineage_names":["Stowarzyszenie Elektryk\u00f3w Polskich"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"PRZEGL\u0104D ELEKTROTECHNICZNY","raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W2105590108"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"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/A5076988108","display_name":"Behrooz Masoumi","orcid":"https://orcid.org/0000-0003-2314-283X","observed_orcids":["https://orcid.org/0000-0003-2314-283X"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Behrooz Masoumi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008824437","display_name":"Mohammad Reza Meybodi","orcid":"https://orcid.org/0000-0003-3775-5565","observed_orcids":["https://orcid.org/0000-0003-3775-5565"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Mohammad Reza Meybodi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033391525","display_name":"Farnaz Abtahi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Farnaz Abtahi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"reviewed_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"280","last_page":"289"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0005000000237487257,"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/learning-automata","display_name":"learning automata","score":0.9980000257492065},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.8880000114440918},{"id":"https://openalex.org/keywords/optimal-policy-learning","display_name":"optimal policy learning","score":0.718999981880188},{"id":"https://openalex.org/keywords/directed-graphs","display_name":"directed graphs","score":0.531000018119812},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5879999995231628},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.7129999995231628}],"concepts":[{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.7958910465240479},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7314399480819702},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6671116352081299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6566404104232788},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.6500664353370667},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6461259722709656},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5395537614822388},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.516404926776886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.503384530544281},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4715181589126587},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4525038003921509},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4256262183189392},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4227150082588196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3862431049346924},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3545162081718445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2543736696243286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23920267820358276},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:2105590108","doi":null,"is_oa":false,"landing_page_url":"http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.baztech-article-BPOK-0039-0066","pdf_url":null,"source":{"id":"https://openalex.org/S197975706","display_name":"PRZEGL\u0104D ELEKTROTECHNICZNY","issn_l":"0033-2097","issn":["0033-2097","2449-9544"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["erih-plus","norway-1","poland-70","russia-white-list-4"],"host_organization":"https://openalex.org/P4310317252","host_organization_name":"Stowarzyszenie Elektryk\u00f3w Polskich","host_organization_lineage":["https://openalex.org/P4310317252"],"host_organization_lineage_names":["Stowarzyszenie Elektryk\u00f3w Polskich"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"PRZEGL\u0104D ELEKTROTECHNICZNY","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.420.2872","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.420.2872","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ceit.aut.ac.ir/~meybodi/paper/Masoumi-Meybodi-Abtahi-Electrical Reveiw-2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1521003796","https://openalex.org/W1538558539","https://openalex.org/W1541580851","https://openalex.org/W1542941925","https://openalex.org/W1560074431","https://openalex.org/W2028145673","https://openalex.org/W2093266575","https://openalex.org/W2095996069","https://openalex.org/W2101130101","https://openalex.org/W2104602264","https://openalex.org/W2105703084","https://openalex.org/W2107544712","https://openalex.org/W2109100253","https://openalex.org/W2113618211","https://openalex.org/W2120846115","https://openalex.org/W2124152208","https://openalex.org/W2128643385","https://openalex.org/W2129734527","https://openalex.org/W2142953473","https://openalex.org/W2145067550","https://openalex.org/W2154803134","https://openalex.org/W2159983624","https://openalex.org/W2169194711","https://openalex.org/W2484003876","https://openalex.org/W2575731723"],"related_works":["https://openalex.org/W2106222893","https://openalex.org/W2140334996","https://openalex.org/W7099471700","https://openalex.org/W2384510608","https://openalex.org/W1542941925","https://openalex.org/W2124152208","https://openalex.org/W3092429416","https://openalex.org/W7124163602","https://openalex.org/W7099176330"],"abstract_inverted_index":{"Abstract.":[0],"Markov":[1,7,39,47],"games,":[2],"as":[3,51],"the":[4,11,44,57,60,63,66,70,84,117,123,132,145,149,158,161,170,174,177,192,195,200,204,207,216,222,233,237],"generalization":[5],"of":[6,62,83,102,131,160,173,179,194,206,211,230,235],"decision":[8],"processes":[9],"to":[10,79,98,111,115,165,190,199],"multi":[12],"agent":[13,106,124,150],"case,":[14],"have":[15,213],"long":[16],"been":[17,182],"used":[18],"for":[19,33],"modeling":[20],"multi-agent":[21,30,188],"systems.":[22],"In":[23,43,120,169],"this":[24],"paper,":[25],"several":[26],"learning":[27,92,133,142,167,185,224],"automata":[28,93,143,186,225],"based":[29,156,187,226],"system":[31],"algorithms":[32,218,227],"finding":[34],"optimal":[35,238],"policies":[36],"in":[37,55,74,135,228],"fully-cooperative":[38],"Games":[40],"are":[41,59,96],"proposed.":[42],"proposed":[45,175,217],"algorithms,":[46,176],"problem":[48],"is":[49,86,151],"described":[50],"a":[52,89,166],"directed":[53,67],"graph":[54],"which":[56],"nodes":[58],"states":[61,101],"problem,":[64],"and":[65,113,202,232],"edges":[68],"represent":[69],"actions":[71,95,139],"that":[72,103,136,215],"result":[73],"transition":[75,128],"from":[76,108],"one":[77,109],"state":[78,82,110],"another.":[80],"Each":[81,105],"environment":[85],"equipped":[87],"with":[88,129],"variable":[90],"structure":[91],"whose":[94],"moving":[97],"different":[99],"adjacent":[100],"state.":[104,119,137],"moves":[107],"another":[112],"tries":[114],"reach":[116],"goal":[118],"each":[121],"state,":[122],"chooses":[125],"its":[126],"next":[127],"help":[130],"automaton":[134],"The":[138,209],"taken":[140],"by":[141,148],"along":[144],"path":[146,163],"traveled":[147,162],"then":[152],"rewarded":[153],"or":[154],"penalized":[155],"on":[157],"value":[159],"according":[164],"algorithm.":[168],"second":[171],"group":[172],"concept":[178],"entropy":[180],"has":[181],"imported":[183],"into":[184],"systems":[189],"drive":[191],"magnitude":[193],"reinforcement":[196],"signal":[197],"given":[198],"LA":[201],"improve":[203],"performance":[205],"algorithms.":[208],"results":[210],"experiments":[212],"shown":[214],"perform":[219],"better":[220],"than":[221],"existing":[223],"terms":[229],"speed":[231],"accuracy":[234],"reaching":[236],"policy.":[239]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2105590108","counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-21T10:27:49.728292","created_date":"2016-06-24T00:00:00"}
