{"id":"https://openalex.org/W2144566660","doi":"https://doi.org/10.1109/icara.2000.4803979","title":"Representation of the perceived environment and acquisition of behavior rule for multi-agent systems by Q-learning","display_name":"Representation of the perceived environment and acquisition of behavior rule for multi-agent systems by Q-learning","publication_year":2009,"publication_date":"2009-02-01","ids":{"openalex":"https://openalex.org/W2144566660","doi":"https://doi.org/10.1109/icara.2000.4803979","mag":"2144566660"},"language":"en","primary_location":{"id":"doi:10.1109/icara.2000.4803979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara.2000.4803979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 4th International Conference on Autonomous Robots and Agents","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/A5112082059","display_name":"Mengchun Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122423","display_name":"National College of Technology, Wakayama College","ror":"https://ror.org/02r033j14","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210122423"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mengchun Xie","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Wakayama National College of Technology, Gobo, Japan","Department of Electrical and Computer Engineering, Wakayama National College of Technology, Noshima 77, Nada-Cho, Gobo City, 644-0023, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Wakayama National College of Technology, Gobo, Japan","institution_ids":["https://openalex.org/I4210122423"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Wakayama National College of Technology, Noshima 77, Nada-Cho, Gobo City, 644-0023, Japan","institution_ids":["https://openalex.org/I4210122423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5112082059"],"corresponding_institution_ids":["https://openalex.org/I4210122423"],"apc_list":null,"apc_paid":null,"fwci":0.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74261811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"453","last_page":"457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9970999956130981,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.9846000075340271,"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/computer-science","display_name":"Computer science","score":0.7612415552139282},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7311275601387024},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7295263409614563},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6944101452827454},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6436854600906372},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.630765974521637},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6182237267494202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6010599136352539},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5809836387634277},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44163891673088074},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4391753077507019},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.42677533626556396},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11950775980949402}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612415552139282},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7311275601387024},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7295263409614563},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6944101452827454},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6436854600906372},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.630765974521637},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6182237267494202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6010599136352539},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5809836387634277},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44163891673088074},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4391753077507019},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.42677533626556396},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11950775980949402},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icara.2000.4803979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara.2000.4803979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 4th International Conference on Autonomous Robots and Agents","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":18,"referenced_works":["https://openalex.org/W114908244","https://openalex.org/W2008824810","https://openalex.org/W2033689783","https://openalex.org/W2057587757","https://openalex.org/W2105665931","https://openalex.org/W2117179645","https://openalex.org/W2128672031","https://openalex.org/W2144726177","https://openalex.org/W2147492008","https://openalex.org/W2158548602","https://openalex.org/W2165752741","https://openalex.org/W2936405433","https://openalex.org/W2965373912","https://openalex.org/W3011120880","https://openalex.org/W6604709212","https://openalex.org/W6683443546","https://openalex.org/W6766479208","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W4206233823","https://openalex.org/W2494202692","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W2786230833","https://openalex.org/W3203256658","https://openalex.org/W2352650970"],"abstract_inverted_index":{"Multiple":[0],"autonomous":[1,134],"robotic":[2],"systems":[3],"can":[4],"be":[5],"represented":[6],"by":[7,73,159],"multi-agent.":[8],"In":[9,38],"multi-agents":[10],"systems,":[11],"each":[12],"agent":[13,106],"must":[14,26],"behave":[15],"independently":[16],"according":[17],"to":[18,33,67,69,91,98],"its":[19],"states":[20],"and":[21,78,140,162],"environments,":[22],"and,":[23],"if":[24],"necessary,":[25],"cooperate":[27],"with":[28,75],"other":[29],"agents":[30,53,66,135],"in":[31,50],"order":[32],"perform":[34],"a":[35,71,85,112],"given":[36],"task.":[37],"the":[39,45,76,93,104,108,119,133,142,145,149,155,163,167],"present":[40],"study,":[41],"we":[42,88,152],"focused":[43],"on":[44,148],"problem":[46],"of":[47,95,115,122,144,166],"ldquotrash":[48],"collectionrdquo,":[49],"which":[51,110],"multiple":[52,65],"collect":[54],"all":[55],"trash":[56],"as":[57,59],"quickly":[58],"possible.":[60],"The":[61],"goal":[62],"is":[63,111],"for":[64,84],"learn":[68],"accomplish":[70],"task":[72],"interacting":[74],"environment":[77,121],"acquiring":[79],"cooperative":[80,96],"behavior":[81],"rules.":[82],"Therefore,":[83],"multi-agent":[86],"system,":[87],"discuss":[89,153],"how":[90,132,154],"acquire":[92],"rules":[94,139],"action":[97,138],"solve":[99],"problems":[100],"effectively.":[101],"We":[102,129],"construct":[103],"learning":[105,146,160],"using":[107],"Q-learning":[109],"representative":[113],"technique":[114],"reinforcement":[116],"learning.":[117],"Regarding":[118],"perceived":[120],"agent,":[123],"two":[124],"representation":[125],"methods":[126],"are":[127],"used.":[128],"then":[130],"observe":[131],"obtain":[136],"their":[137],"examined":[141],"influence":[143],"situations":[147],"system.":[150],"Moreover,":[151],"system":[156],"was":[157],"influenced":[158],"situation":[161],"view":[164],"information":[165],"agent.":[168]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}