{"id":"https://openalex.org/W2391666574","doi":null,"title":"Reinforcement Learning Technology in Multi-Agent System","display_name":"Reinforcement Learning Technology in Multi-Agent System","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2391666574","mag":"2391666574"},"language":"en","primary_location":{"id":"mag:2391666574","doi":null,"is_oa":false,"landing_page_url":"http://en.cnki.com.cn/Article_en/CJFDTOTAL-JSJA200403005.htm","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Computer Science","raw_type":null},"volume":null,"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":null,"display_name":"Zhidan Zhao","orcid":"https://orcid.org/0000-0002-6835-0774","observed_orcids":["https://orcid.org/0000-0002-6835-0774"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhidan Zhao","raw_affiliation_strings":["-Hong GAO Yang LUO Bin CHEN Shi-Fu"],"raw_orcid":"https://orcid.org/0000-0002-6835-0774","affiliations":[{"raw_affiliation_string":"-Hong GAO Yang LUO Bin CHEN Shi-Fu","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3256,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71550466,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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":0.9980000257492065},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.9990000128746033},{"id":"https://openalex.org/keywords/reinforcement-learning-algorithms","display_name":"reinforcement learning algorithms","score":0.9700000286102295},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.6769999861717224}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9463670253753662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586064577102661},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6734219789505005},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.5311067700386047},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4725615382194519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4650259017944336},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.42565488815307617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3309030532836914},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2391666574","doi":null,"is_oa":false,"landing_page_url":"http://en.cnki.com.cn/Article_en/CJFDTOTAL-JSJA200403005.htm","pdf_url":null,"source":null,"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7005533258","https://openalex.org/W7098557977","https://openalex.org/W4407741524","https://openalex.org/W2186803321","https://openalex.org/W4399770676","https://openalex.org/W6920475523","https://openalex.org/W1744965757","https://openalex.org/W2291763734","https://openalex.org/W2054432309","https://openalex.org/W2099618002"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,9,12,16,23,30,33,43,52,67],"key":[4],"techniques,the":[5],"current":[6],"state":[7],"of":[8,15,32],"research":[10],"and":[11,19,45],"development":[13],"tendency":[14],"reinforcement":[17,34,39,48,63],"learning":[18,40,49,64],"its":[20],"applications":[21,44],"in":[22,51,66],"multi-agent":[24,53,68],"system.":[25,54],"The":[26],"content":[27],"includes;":[28],"(1)":[29],"structure":[31],"learning;":[35],"(2)":[36],"several":[37],"representative":[38],"algorithms;":[41],"(3)":[42],"problems":[46],"adopting":[47,62],"algorithms":[50,65],"Finally,the":[55],"challenge":[56],"that":[57],"will":[58],"be":[59],"encountered":[60],"when":[61],"system":[69],"is":[70],"discussed.":[71]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2016-06-24T00:00:00"}