{"id":"https://openalex.org/W2009988656","doi":"https://doi.org/10.1142/s0219525911002937","title":"ACTION DISCOVERY FOR SINGLE AND MULTI-AGENT REINFORCEMENT LEARNING","display_name":"ACTION DISCOVERY FOR SINGLE AND MULTI-AGENT REINFORCEMENT LEARNING","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2009988656","doi":"https://doi.org/10.1142/s0219525911002937","mag":"2009988656"},"language":"en","primary_location":{"id":"doi:10.1142/s0219525911002937","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525911002937","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","raw_type":"journal-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/A5025954824","display_name":"Bikramjit Banerjee","orcid":"https://orcid.org/0000-0001-7999-0307"},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"BIKRAMJIT BANERJEE","raw_affiliation_strings":["School of Computing, The University of Southern Mississippi, Hattiesburg, MS 39406-0001, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, The University of Southern Mississippi, Hattiesburg, MS 39406-0001, USA","institution_ids":["https://openalex.org/I44854399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048144212","display_name":"Landon Kraemer","orcid":null},"institutions":[{"id":"https://openalex.org/I44854399","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I44854399"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"LANDON KRAEMER","raw_affiliation_strings":["School of Computing, The University of Southern Mississippi, Hattiesburg, MS 39406-0001, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, The University of Southern Mississippi, Hattiesburg, MS 39406-0001, USA","institution_ids":["https://openalex.org/I44854399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44854399"],"apc_list":null,"apc_paid":null,"fwci":0.4559,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76219423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"14","issue":"02","first_page":"279","last_page":"305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.996999979019165,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9901000261306763,"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":0.8854308724403381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7104225158691406},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6593509316444397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5731281042098999},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5578005909919739},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5476150512695312},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5273274779319763},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5256736874580383},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5127342939376831},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46568384766578674},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.44095608592033386},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4385736286640167},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07458490133285522}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8854308724403381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7104225158691406},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6593509316444397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5731281042098999},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5578005909919739},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5476150512695312},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5273274779319763},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5256736874580383},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5127342939376831},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46568384766578674},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.44095608592033386},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4385736286640167},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07458490133285522},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1142/s0219525911002937","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525911002937","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","raw_type":"journal-article"},{"id":"pmh:oai:aquila.usm.edu:fac_pubs-1323","is_oa":false,"landing_page_url":"https://aquila.usm.edu/fac_pubs/324","pdf_url":null,"source":{"id":"https://openalex.org/S4306402529","display_name":"Aquila Digital Community (University of Southern Mississippi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I44854399","host_organization_name":"University of Southern Mississippi","host_organization_lineage":["https://openalex.org/I44854399"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:RePEc:wsi:acsxxx:v:14:y:2011:i:02:n:s0219525911002937","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S0219525911002937","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:RePEc:wsi:acsxxx:v:14:y:2011:i:02:p:279-305","is_oa":false,"landing_page_url":"http://www.worldscinet.com/cgi-bin/details.cgi?type=html&id=pii:S0219525911002937","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309142","display_name":"University of Southern Mississippi","ror":"https://ror.org/0270vfa57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W34013550","https://openalex.org/W1484740474","https://openalex.org/W1542941925","https://openalex.org/W1777239053","https://openalex.org/W2104602264","https://openalex.org/W2109102709","https://openalex.org/W2109910161","https://openalex.org/W2117341272","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2130750514","https://openalex.org/W2131600418","https://openalex.org/W2156289698","https://openalex.org/W2165792602","https://openalex.org/W2787259794","https://openalex.org/W3103379718","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2607437843","https://openalex.org/W4295700147","https://openalex.org/W2963162727","https://openalex.org/W2037601570","https://openalex.org/W2912947802","https://openalex.org/W2123856982","https://openalex.org/W2877093712"],"abstract_inverted_index":{"The":[0],"design":[1],"of":[2,40,48,116,161],"reinforcement":[3,102,148],"learning":[4,103],"solutions":[5],"to":[6,15,20,74,130,146],"many":[7],"problems":[8,137],"artificially":[9],"constrain":[10],"the":[11,22,38,46,49,56,65,91,95,114],"action":[12,43,107,144,171],"set":[13],"available":[14],"an":[16,28],"agent,":[17],"in":[18,81,173],"order":[19],"limit":[21],"exploration/sample":[23],"complexity.":[24,67],"While":[25],"exploring,":[26],"if":[27],"agent":[29],"can":[30,35],"discover":[31],"new":[32],"actions":[33,62],"that":[34,89,152],"break":[36],"through":[37],"constraints":[39],"its":[41],"basic/atomic":[42],"set,":[44],"then":[45],"quality":[47,93,163],"learned":[50],"decision":[51,117],"policy":[52],"could":[53],"improve.":[54],"On":[55],"flipside,":[57],"considering":[58],"all":[59],"possible":[60],"non-atomic":[61],"might":[63],"explode":[64],"exploration":[66],"We":[68,150],"present":[69],"a":[70,174],"novel":[71],"heuristic":[72],"solution":[73,92],"this":[75,141],"dilemma,":[76],"and":[77,94],"empirically":[78],"evaluate":[79],"it":[80],"grid":[82],"navigation":[83],"tasks.":[84],"In":[85],"particular,":[86],"we":[87,142],"show":[88,151],"both":[90],"sample":[96,166],"complexity":[97,167],"improve":[98],"significantly":[99],"when":[100,168],"basic":[101],"is":[104,120],"coupled":[105,169],"with":[106,134,164,170],"discovery.":[108],"Our":[109],"approach":[110],"relies":[111],"on":[112],"reducing":[113],"number":[115],"points,":[118],"which":[119],"particularly":[121],"suited":[122],"for":[123],"multiagent":[124],"coordination":[125,136,159],"learning,":[126],"since":[127],"agents":[128],"tend":[129],"learn":[131,158],"more":[132],"easily":[133],"fewer":[135],"(CPs).":[138],"To":[139],"demonstrate":[140],"extend":[143],"discovery":[145],"multi-agent":[147,175],"learning.":[149],"Joint":[153],"Action":[154],"Learners":[155],"(JALs)":[156],"indeed":[157],"policies":[160],"higher":[162],"lower":[165],"discovery,":[172],"box-pushing":[176],"task.":[177]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}