{"id":"https://openalex.org/W2120153538","doi":"https://doi.org/10.1109/icnc.2011.6022301","title":"Cooperative multi-agent reinforcement learning based on online heuristic extraction","display_name":"Cooperative multi-agent reinforcement learning based on online heuristic extraction","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2120153538","doi":"https://doi.org/10.1109/icnc.2011.6022301","mag":"2120153538"},"language":"en","primary_location":{"id":"doi:10.1109/icnc.2011.6022301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnc.2011.6022301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Seventh International Conference on Natural Computation","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/A5021284542","display_name":"Jun Wu","orcid":"https://orcid.org/0000-0002-1388-7451"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Wu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, P.R China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, P.R China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, P.R China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, P.R China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044447816","display_name":"Zhenping Sun","orcid":"https://orcid.org/0009-0009-1491-5280"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-ping Sun","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, P.R China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, P.R China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012678483","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-5548-2727"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, P.R China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, P.R China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021284542"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12479951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"1299","last_page":"1303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.988099992275238,"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":0.880499541759491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7601422071456909},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6952970027923584},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6606655716896057},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6193334460258484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.599274218082428},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.556871235370636},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5559282898902893},{"id":"https://openalex.org/keywords/hyper-heuristic","display_name":"Hyper-heuristic","score":0.5037402510643005},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4403536319732666},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42902353405952454},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32943660020828247},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.25788772106170654},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10186636447906494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09315067529678345}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.880499541759491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601422071456909},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6952970027923584},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6606655716896057},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6193334460258484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599274218082428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.556871235370636},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5559282898902893},{"id":"https://openalex.org/C117270229","wikidata":"https://www.wikidata.org/wiki/Q5957539","display_name":"Hyper-heuristic","level":5,"score":0.5037402510643005},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4403536319732666},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42902353405952454},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32943660020828247},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.25788772106170654},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10186636447906494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09315067529678345},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"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/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnc.2011.6022301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnc.2011.6022301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Seventh International Conference on Natural Computation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W29099680","https://openalex.org/W1973039793","https://openalex.org/W2053407718","https://openalex.org/W2099144379","https://openalex.org/W2118556122","https://openalex.org/W2120327309","https://openalex.org/W2151340488","https://openalex.org/W2793955907","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3038611842","https://openalex.org/W4242606736","https://openalex.org/W4285719527","https://openalex.org/W4301630257","https://openalex.org/W6601161420"],"related_works":["https://openalex.org/W3177062893","https://openalex.org/W3125143773","https://openalex.org/W2007032764","https://openalex.org/W803550684","https://openalex.org/W2483226803","https://openalex.org/W4352977312","https://openalex.org/W1536056491","https://openalex.org/W2041180560","https://openalex.org/W2586529194","https://openalex.org/W1628567638"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,24,29,71,79,86,97],"has":[2],"been":[3],"an":[4],"important":[5],"technique":[6],"for":[7],"adaptive":[8],"decision-making":[9],"of":[10,19],"multi-agent":[11,22,69],"systems":[12],"in":[13,21],"uncertain":[14],"environments.":[15],"However,":[16],"the":[17,27,46,78,91],"curse":[18],"dimensionality":[20],"reinforcement":[23,70],"usually":[25],"causes":[26],"slow":[28],"convergence":[30,98],"or":[31,66],"even":[32],"failure.":[33],"In":[34],"this":[35],"paper,":[36],"a":[37,51,64,84,94],"novel":[38],"Online":[39],"Heuristics":[40],"Extraction":[41],"method,":[42,93],"which":[43],"can":[44,60,99],"integrate":[45],"prior":[47],"heuristic":[48,53],"policy":[49],"with":[50,90],"learned":[52],"policy,":[54],"is":[55],"presented.":[56],"The":[57],"new":[58,92],"method":[59],"be":[61,100],"incorporated":[62],"into":[63],"tabular":[65],"approximate":[67],"cooperative":[68,85],"algorithm":[72],"so":[73],"as":[74],"to":[75],"speed":[76],"up":[77],"process.":[80],"Simulation":[81],"results":[82],"on":[83],"task":[87],"show":[88],"that,":[89],"much":[95],"better":[96],"achieved.":[101]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}