{"id":"https://openalex.org/W1547108555","doi":"https://doi.org/10.1109/icsmc.2003.1244340","title":"Q-ac: multiagent reinforcement learning with perception-conversion action","display_name":"Q-ac: multiagent reinforcement learning with perception-conversion action","publication_year":2004,"publication_date":"2004-05-13","ids":{"openalex":"https://openalex.org/W1547108555","doi":"https://doi.org/10.1109/icsmc.2003.1244340","mag":"1547108555"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2003.1244340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2003.1244340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483)","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/A5053672295","display_name":"Ricky Sun","orcid":"https://orcid.org/0009-0004-3025-4500"},"institutions":[{"id":"https://openalex.org/I317356780","display_name":"Osaka City University","ror":"https://ror.org/02skfsw40","country_code":"JP","type":"education","lineage":["https://openalex.org/I317356780"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"R. Sun","raw_affiliation_strings":["Faculty of Engineering, Osaka City University, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Osaka City University, Osaka, Japan","institution_ids":["https://openalex.org/I317356780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103617309","display_name":"Shoji Tatsumi","orcid":null},"institutions":[{"id":"https://openalex.org/I317356780","display_name":"Osaka City University","ror":"https://ror.org/02skfsw40","country_code":"JP","type":"education","lineage":["https://openalex.org/I317356780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Tatsumi","raw_affiliation_strings":["Faculty of Engineering, Osaka City University, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Osaka City University, Osaka, Japan","institution_ids":["https://openalex.org/I317356780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101897965","display_name":"Gang Zhao","orcid":"https://orcid.org/0000-0003-1194-3226"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gang Zhao","raw_affiliation_strings":["Fujitsu Kansai-chubu Net-tech Limited, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Kansai-chubu Net-tech Limited, Osaka, Japan","institution_ids":["https://openalex.org/I2252096349"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053672295"],"corresponding_institution_ids":["https://openalex.org/I317356780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.06048625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"2950","last_page":"2955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.954800009727478,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9538000226020813,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.858492374420166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7416553497314453},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.578014612197876},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5661358833312988},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.5560643672943115},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5481963753700256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5159626603126526},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.49389129877090454},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4930846393108368},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.48633700609207153},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4849100708961487},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43886151909828186},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.35158276557922363},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3362640142440796},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1284199357032776},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12281426787376404},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06511002779006958},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.061050742864608765}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.858492374420166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416553497314453},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.578014612197876},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5661358833312988},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5560643672943115},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5481963753700256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5159626603126526},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.49389129877090454},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4930846393108368},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48633700609207153},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4849100708961487},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43886151909828186},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.35158276557922363},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3362640142440796},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1284199357032776},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12281426787376404},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06511002779006958},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.061050742864608765},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2003.1244340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2003.1244340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1557517019","https://openalex.org/W1641379095","https://openalex.org/W1739538851","https://openalex.org/W2009533501","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2103791569","https://openalex.org/W2107726111","https://openalex.org/W2154929945","https://openalex.org/W2610686804","https://openalex.org/W3041202696","https://openalex.org/W6637856732","https://openalex.org/W6674995601"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W2937181779"],"abstract_inverted_index":{"For":[0],"the":[1,43,47,65,69,85,96,116,137,140,148,159,162],"task":[2,48],"under":[3],"Markov":[4],"Decision":[5],"Process,":[6],"this":[7,54],"paper":[8,55],"presents":[9],"a":[10,101],"novel":[11],"multiagent":[12,102,106],"Reinforcement":[13],"Learning":[14],"(RL)":[15],"with":[16],"perception":[17,112],"and":[18,28,68,113,122,139],"conversion":[19,114],"action":[20,31,36,150],"mechanism":[21],"that":[22],"learning":[23,33,51,61,117,120],"agents":[24,62,118],"observe":[25],"adversary":[26,44],"agent":[27,45],"convert":[29],"adversarial":[30],"to":[32,73,136],"agents'":[34,75,133,145],"corresponding":[35],"as":[37],"observing":[38],"state":[39],"variation":[40],"incurred":[41],"by":[42,82,91,126],"in":[46],"environment":[49,98],"during":[50],"processes.":[52],"Meanwhile,":[53],"surveys":[56],"inexpensive":[57],"communication":[58,67,72,79,88,131,143],"ways":[59],"among":[60],"utilizing":[63],"both":[64],"direct":[66,78,130],"indirect":[70,86,141],"media":[71,87,142],"realize":[74],"cooperation.":[76],"The":[77,129,152],"is":[80,89,109],"realized":[81,90],"sharing":[83],"sensation;":[84],"updating":[92],"reinforcement":[93],"values":[94],"on":[95,155],"common":[97],"observation.":[99],"Then,":[100],"RL":[103,107],"algorithm,":[104],"Q-ac":[105],"method,":[108],"proposed.":[110],"By":[111],"action,":[115],"extend":[119],"episodes":[121],"derive":[123],"more":[124],"observation":[125,134],"less":[127],"action.":[128],"enhances":[132],"ability":[135,146],"environment,":[138],"improves":[144],"deriving":[147],"optimal":[149],"policy.":[151],"simulation":[153],"results":[154],"hunter":[156],"game":[157],"demonstrate":[158],"efficiency":[160],"of":[161],"proposed":[163],"method.":[164]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}