{"id":"https://openalex.org/W2392415905","doi":null,"title":"Research on Q Learning Algorithm with Sharing Experience in Learning Process","display_name":"Research on Q Learning Algorithm with Sharing Experience in Learning Process","alternate_titles":[],"publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2392415905","mag":"2392415905"},"language":"en","primary_location":{"id":"mag:2392415905","doi":null,"is_oa":false,"landing_page_url":"https://oversea.cnki.net/kcms/detail/detail.aspx?dbcode=CJFD&filename=JSJA201205053","pdf_url":null,"source":{"id":"https://openalex.org/S4306515071","display_name":"Jisuanji Kexue","issn_l":"1002-137X","issn":["1002-137X"],"is_oa":false,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Computer Science","raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W2392415905"],"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/A5101722546","display_name":"Jie Luo","orcid":"https://orcid.org/0000-0002-4523-245X","observed_orcids":["https://orcid.org/0000-0002-4523-245X"]},"institutions":[],"countries":[],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"Jie Luo","raw_affiliation_strings":["Telecommunications,Nanjing 210046,China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telecommunications,Nanjing 210046,China)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5101722546"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2335,"has_fulltext":false,"cited_by_count":2,"reviewed_by_count":0,"citation_normalized_percentile":{"value":0.5174466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":86,"max":92},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9984999895095825,"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":0.9984999895095825,"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":0.00039999998989515007,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.00019999999494757503,"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/q-learning","display_name":"Q-learning","score":0.8650000095367432},{"id":"https://openalex.org/keywords/multi-agent-learning","display_name":"multi-agent learning","score":0.8389999866485596},{"id":"https://openalex.org/keywords/experience-sharing","display_name":"experience sharing","score":0.9800000190734863},{"id":"https://openalex.org/keywords/pursuit-problem","display_name":"pursuit problem","score":0.6830000281333923},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"cooperative learning","score":0.5720000267028809},{"id":"https://openalex.org/keywords/stages-of-learning","display_name":"learning stages","score":0.5490000247955322},{"id":"https://openalex.org/keywords/strategy-convergence","display_name":"strategy convergence","score":0.6869999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8859621286392212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6064904928207397},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.6053776144981384},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5866204500198364},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5825615525245667},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5651792287826538},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5281130075454712},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5082678198814392},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4228290319442749},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.13880467414855957},{"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/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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2392415905","doi":null,"is_oa":false,"landing_page_url":"https://oversea.cnki.net/kcms/detail/detail.aspx?dbcode=CJFD&filename=JSJA201205053","pdf_url":null,"source":{"id":"https://openalex.org/S4306515071","display_name":"Jisuanji Kexue","issn_l":"1002-137X","issn":["1002-137X"],"is_oa":false,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Computer Science","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2889177340","https://openalex.org/W2352065305","https://openalex.org/W2380374763","https://openalex.org/W2377651198","https://openalex.org/W8539471","https://openalex.org/W2351098378","https://openalex.org/W2347960316","https://openalex.org/W2356109118","https://openalex.org/W2357597048","https://openalex.org/W2771654806"],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,10,18,33,44,90,113,135],"the":[3,8,26,46,48,87,100,111,114,122,133,142],"research":[4],"is":[5,61,116],"to":[6,85,141],"improve":[7,132],"efficience":[9],"multi-agent":[11,19],"Q-learing":[12],"algorithm.This":[13],"paper":[14],"proposed":[15],"a":[16,34,40,66,71],"method":[17],"Q-learning":[20,123],"with":[21,80,125],"sharing":[22,126],"experience":[23,76,127],"based":[24],"on":[25],"pursuit":[27],"problem.This":[28],"algorithm":[29,124],"simulats":[30],"human":[31],"behavior":[32],"learning":[35,59,67,75,129,136],"team,and":[36],"all":[37],"agents":[38,92],"share":[39],"common":[41],"utimate":[42],"goal":[43],"capturing":[45],"prey,at":[47],"same":[49],"time":[50],"every":[51],"agent":[52],"gets":[53],"their":[54],"own":[55],"milestones":[56],"through":[57],"negotiations.The":[58],"process":[60,130],"divided":[62],"into":[63],"some":[64],"stages.After":[65],"stage,there":[68],"will":[69,77],"be":[70,78],"stage":[72,89],"summary.Then":[73],"good":[74],"shared":[79],"each":[81],"other":[82],"in":[83,108,128],"order":[84],"facilitate":[86],"next":[88],"learning.The":[91],"who":[93,102],"learn":[94,103],"fast":[95],"and":[96,105,138],"well":[97],"can":[98,131],"help":[99],"ones":[101],"slow":[104],"not":[106],"well,so":[107],"this":[109],"way":[110],"performance":[112,134],"system":[115],"enhanced.The":[117],"simulation":[118],"results":[119],"prove":[120],"that":[121],"systems":[137],"efficient":[139],"convergence":[140],"optimal":[143],"strategy.":[144]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2392415905","counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
