{"id":"https://openalex.org/W87513465","doi":null,"title":"Investigating reinforcement learning in multiagent coalition formation","display_name":"Investigating reinforcement learning in multiagent coalition formation","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W87513465","mag":"87513465"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.4058","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.4058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/Workshops/2004/WS-04-06/WS04-06-004.pdf","raw_type":"text"},"volume":null,"type":"conference-paper","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":"Xin Li","orcid":"https://orcid.org/0000-0002-0041-3134","observed_orcids":["https://orcid.org/0000-0002-0041-3134"]},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["#N##TAB##TAB##TAB##TAB# University of Nebraska-Lincoln#N##TAB##TAB##TAB#"],"raw_orcid":"https://orcid.org/0000-0002-0041-3134","affiliations":[{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# University of Nebraska-Lincoln#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112287180","display_name":"Leen Kiat Soh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leen Kiat Soh","raw_affiliation_strings":["Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1871,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.75934823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"22","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.5220000147819519,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.5220000147819519,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.44600000977516174,"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/T10991","display_name":"Game Theory and Voting Systems","score":0.006099999882280827,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9290000200271606},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"case-based reasoning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.5699999928474426},{"id":"https://openalex.org/keywords/dynamic-and-uncertain-environments","display_name":"dynamic uncertain environments","score":0.8349999785423279},{"id":"https://openalex.org/keywords/real-time-learning","display_name":"real-time learning","score":0.6320000290870667},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.6209999918937683}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9418551921844482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6482774019241333},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.63215172290802},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.5760596990585327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49253401160240173},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1515215039253235},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.4058","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.4058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/Workshops/2004/WS-04-06/WS04-06-004.pdf","raw_type":"text"},{"id":"mag:87513465","doi":null,"is_oa":false,"landing_page_url":"https://www.aaai.org/Papers/Workshops/2004/WS-04-06/WS04-06-004.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"National Conference on Artificial Intelligence","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":19,"referenced_works":["https://openalex.org/W126344362","https://openalex.org/W200679011","https://openalex.org/W1546574211","https://openalex.org/W1556191380","https://openalex.org/W1556565860","https://openalex.org/W1571787852","https://openalex.org/W1598724299","https://openalex.org/W1641379095","https://openalex.org/W1681475672","https://openalex.org/W1963576113","https://openalex.org/W1971441460","https://openalex.org/W2053616263","https://openalex.org/W2060993401","https://openalex.org/W2107726111","https://openalex.org/W2108232579","https://openalex.org/W2146482048","https://openalex.org/W2147492008","https://openalex.org/W2156102177","https://openalex.org/W2615688110"],"related_works":["https://openalex.org/W7097435455","https://openalex.org/W7097191568","https://openalex.org/W938118831","https://openalex.org/W2004391580","https://openalex.org/W1592455152","https://openalex.org/W2469933366","https://openalex.org/W2040309923","https://openalex.org/W2461194651","https://openalex.org/W7124171798","https://openalex.org/W3176937828"],"abstract_inverted_index":{"In":[0,92],"this":[1,93],"paper":[2,94],"we":[3,31,95,154],"investigate":[4],"the":[5,12,27,36,43,69,75,79,85,102,142,167,179],"use":[6,54],"of":[7,45,101,104,115],"reinforcement":[8,38,49,86,105,116,119,123,159,163],"learning":[9,39,87,106,120,129,134,160,168],"to":[10,26,57,78,126],"address":[11],"multiagent":[13,108],"coalition":[14,60,89,109,149,173],"formation":[15,61,90,174],"problem":[16],"in":[17,63,107,170],"dynamic,":[18],"uncertain,":[19],"real-time,":[20],"and":[21,48,72,81,121,131,161,176],"noisy":[22],"environments.":[23],"To":[24],"adapt":[25],"complex":[28],"environmental":[29],"factors,":[30],"equip":[32],"each":[33],"agent":[34,52,138],"with":[35,84],"case-based":[37,46,55],"ability":[40],"which":[41],"is":[42],"integration":[44],"reasoning":[47,56],"learning.":[50,164],"The":[51],"can":[53],"derive":[58],"a":[59,64,152,171],"plan":[62,76],"real-time":[65],"manner":[66],"based":[67],"on":[68,88,97],"past":[70],"experience,":[71],"then":[73],"instantiate":[74],"adapting":[77],"dynamic":[80],"uncertain":[82],"environment":[83],"experience.":[91],"focus":[96],"describing":[98],"multiple":[99],"aspects":[100],"application":[103],"formation.":[110],"We":[111,165],"classify":[112],"two":[113],"types":[114],"learning:":[117],"case-oriented":[118],"peerrelated":[122],"learning,":[124],"corresponding":[125],"strategic,":[127],"off-line":[128],"scenario":[130,135],"tactical,":[132],"online":[133],"respectively.":[136],"An":[137],"might":[139],"learn":[140],"about":[141],"others\u2019":[143],"joint":[144],"or":[145],"individual":[146],"behavior":[147],"during":[148],"formation,":[150],"as":[151,157],"result,":[153],"identify":[155],"them":[156],"joint-behavior":[158],"individual-behavior":[162],"embed":[166],"approach":[169],"multi-phase":[172],"model":[175],"have":[177],"implemented":[178],"approach.":[180]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2016-06-24T00:00:00"}