{"id":"https://openalex.org/W2160024778","doi":"https://doi.org/10.1109/icsmc.2009.5346316","title":"The improvement of Q-learning applied to imperfect information game","display_name":"The improvement of Q-learning applied to imperfect information game","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2160024778","doi":"https://doi.org/10.1109/icsmc.2009.5346316","mag":"2160024778"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2009.5346316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5346316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","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/A5061991728","display_name":"Jing Lin","orcid":"https://orcid.org/0000-0002-7458-6820"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jing Lin","raw_affiliation_strings":["Intelligence Computing Research Center, HIT Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Intelligence Computing Research Center, HIT Shenzhen Graduate School, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113968141","display_name":"Xuan Wang","orcid":"https://orcid.org/0009-0005-4952-4619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuan Wang","raw_affiliation_strings":["Intelligence Computing Research Center, HIT Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Intelligence Computing Research Center, HIT Shenzhen Graduate School, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100529537","display_name":"Lijiao Han","orcid":null},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijiao Han","raw_affiliation_strings":["School of Management, Shenyang University of Technology, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"School of Management, Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417632","display_name":"Jiajia Zhang","orcid":"https://orcid.org/0000-0001-6611-2046"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajia Zhang","raw_affiliation_strings":["Intelligence Computing Research Center, HIT Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Intelligence Computing Research Center, HIT Shenzhen Graduate School, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030908734","display_name":"Xinxin Xu","orcid":"https://orcid.org/0000-0001-7485-6096"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinxin Xu","raw_affiliation_strings":["Intelligence Computing Research Center, HIT Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Intelligence Computing Research Center, HIT Shenzhen Graduate School, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061991728"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.14520369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1562","last_page":"1567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9868000149726868,"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":0.9868000149726868,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9853000044822693,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9708999991416931,"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/perfect-information","display_name":"Perfect information","score":0.7541283965110779},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.7438719868659973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6921747922897339},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.6461704969406128},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6263279914855957},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4460844397544861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41836944222450256},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41465163230895996},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3689122200012207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14309072494506836}],"concepts":[{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.7541283965110779},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.7438719868659973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6921747922897339},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.6461704969406128},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6263279914855957},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4460844397544861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41836944222450256},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41465163230895996},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3689122200012207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14309072494506836},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2009.5346316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5346316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1500885882","https://openalex.org/W1576452626","https://openalex.org/W1706571876","https://openalex.org/W2024060531","https://openalex.org/W2056760934","https://openalex.org/W2070441255","https://openalex.org/W2100677568","https://openalex.org/W2170123469","https://openalex.org/W2382693490","https://openalex.org/W2610686804","https://openalex.org/W2808421695","https://openalex.org/W3041202696","https://openalex.org/W4205326910","https://openalex.org/W6634528131"],"related_works":["https://openalex.org/W2360321812","https://openalex.org/W2395295193","https://openalex.org/W3122057932","https://openalex.org/W2113798763","https://openalex.org/W3088364074","https://openalex.org/W2004230228","https://openalex.org/W2610227658","https://openalex.org/W2145796981","https://openalex.org/W2900431508","https://openalex.org/W2050340470"],"abstract_inverted_index":{"There":[0],"exist":[1],"problems":[2],"of":[3,25,71,101],"slow":[4],"convergence":[5,31],"and":[6,18,33,48,67,107,111],"local":[7,38],"optimum":[8],"in":[9,37],"standard":[10],"Q-learning":[11,43,55],"algorithm.":[12,51],"Truncated":[13],"TD":[14,46],"estimate":[15],"returns":[16],"efficiency":[17],"simulated":[19,49],"annealing":[20,50],"algorithm":[21,30,56],"increase":[22],"the":[23,29,59,93,99],"chance":[24],"exploration.":[26],"To":[27],"accelerate":[28],"speed":[32],"to":[34,92],"avoid":[35],"results":[36],"optimum,":[39],"this":[40,80],"paper":[41],"combines":[42],"algorithm,":[44],"truncated":[45],"estimation":[47],"We":[52],"apply":[53],"improved":[54],"using":[57],"into":[58],"imperfect":[60,72],"information":[61,73],"game":[62,74,89],"(SiGuo":[63],"military":[64],"chess":[65],"game),":[66],"realize":[68],"a":[69],"self-learning":[70],"system.":[75],"Experimental":[76],"outcomes":[77],"show":[78],"that":[79],"system":[81,114],"can":[82],"dynamically":[83],"adjust":[84],"each":[85],"weight":[86],"which":[87],"describes":[88],"state":[90],"according":[91],"results.":[94],"Further,":[95],"it":[96],"speeds":[97],"up":[98],"process":[100],"learning,":[102],"effectively":[103],"simulates":[104],"human":[105],"intelligence":[106],"makes":[108],"reasonable":[109],"step,":[110],"significantly":[112],"improves":[113],"performance.":[115]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}