{"id":"https://openalex.org/W1972847450","doi":"https://doi.org/10.1080/09528130412331297956","title":"On-policy concurrent reinforcement learning","display_name":"On-policy concurrent reinforcement learning","publication_year":2004,"publication_date":"2004-10-01","ids":{"openalex":"https://openalex.org/W1972847450","doi":"https://doi.org/10.1080/09528130412331297956","mag":"1972847450"},"language":"en","primary_location":{"id":"doi:10.1080/09528130412331297956","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09528130412331297956","pdf_url":null,"source":{"id":"https://openalex.org/S153467142","display_name":"Journal of Experimental & Theoretical Artificial Intelligence","issn_l":"0952-813X","issn":["0952-813X","1362-3079"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Experimental & Theoretical Artificial Intelligence","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/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bikramjit Banerjee","raw_affiliation_strings":["EECS Department , Tulane University , New Orleans, LA 70118, USA E-mail: banerjee@eecs.tulane.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS Department , Tulane University , New Orleans, LA 70118, USA E-mail: banerjee@eecs.tulane.edu","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066020533","display_name":"Sandip Sen","orcid":"https://orcid.org/0000-0001-6107-4095"},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandip Sen","raw_affiliation_strings":["MCS Department , University of Tulsa , Tulsa, OK 74104, USA E-mail: sandip@kolkata.mcs.utulsa.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MCS Department , University of Tulsa , Tulsa, OK 74104, USA E-mail: sandip@kolkata.mcs.utulsa.edu","institution_ids":["https://openalex.org/I87208437"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072128915","display_name":"Jing Peng","orcid":"https://orcid.org/0000-0001-5490-6228"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Peng","raw_affiliation_strings":["EECS Department , Tulane University , New Orleans, LA 70118, USA E-mail: jp@eecs.tulane.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS Department , Tulane University , New Orleans, LA 70118, USA E-mail: jp@eecs.tulane.edu","institution_ids":["https://openalex.org/I114832834"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.832,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87151683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"16","issue":"4","first_page":"245","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11182","display_name":"Auction Theory and Applications","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9726999998092651,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8868438005447388},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8807456493377686},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6687642931938171},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.6341261267662048},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5262771248817444},{"id":"https://openalex.org/keywords/cornerstone","display_name":"Cornerstone","score":0.5198912620544434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5183557271957397},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5039801001548767},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4979228973388672},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.46440932154655457},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.43449410796165466},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4236568808555603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3613460659980774},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2550007104873657},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.07700416445732117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8868438005447388},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8807456493377686},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6687642931938171},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.6341261267662048},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5262771248817444},{"id":"https://openalex.org/C2780616401","wikidata":"https://www.wikidata.org/wiki/Q1133673","display_name":"Cornerstone","level":2,"score":0.5198912620544434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5183557271957397},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5039801001548767},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4979228973388672},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.46440932154655457},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43449410796165466},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4236568808555603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3613460659980774},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2550007104873657},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.07700416445732117},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/09528130412331297956","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09528130412331297956","pdf_url":null,"source":{"id":"https://openalex.org/S153467142","display_name":"Journal of Experimental & Theoretical Artificial Intelligence","issn_l":"0952-813X","issn":["0952-813X","1362-3079"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Experimental & Theoretical Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W139877375","https://openalex.org/W146900863","https://openalex.org/W1513468570","https://openalex.org/W1515108343","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1587589241","https://openalex.org/W1646707810","https://openalex.org/W2039355449","https://openalex.org/W2089415692","https://openalex.org/W2110431754","https://openalex.org/W2120327309","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2125074935","https://openalex.org/W2137466452","https://openalex.org/W2139418546","https://openalex.org/W2150339816","https://openalex.org/W2330024298","https://openalex.org/W2610686804","https://openalex.org/W3011120880","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4234761190"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W4287865573","https://openalex.org/W2025663273","https://openalex.org/W3007324819","https://openalex.org/W4230011720","https://openalex.org/W4301668927","https://openalex.org/W2122010238","https://openalex.org/W4288917516","https://openalex.org/W1574958246","https://openalex.org/W2373808749"],"abstract_inverted_index":{"When":[0],"an":[1],"agent":[2],"learns":[3],"in":[4,36,50,124],"a":[5],"multi-agent":[6,37],"environment,":[7],"the":[8,15,18,22,63,77,110,120,130],"payoff":[9],"it":[10,85],"receives":[11],"is":[12,86,105],"dependent":[13],"on":[14],"behaviour":[16],"of":[17,73,79,129],"other":[19,23],"agents.":[20],"If":[21],"agents":[24],"are":[25,92],"also":[26,106],"learning,":[27],"its":[28],"reward":[29],"distribution":[30],"becomes":[31],"non-stationary.":[32],"This":[33,68],"makes":[34],"learning":[35,49],"systems":[38],"more":[39],"difficult":[40],"than":[41,119],"single-agent":[42],"learning.":[43],"Prior":[44],"attempts":[45],"at":[46],"value-function":[47],"based":[48],"such":[51,74],"domains":[52],"have":[53],"used":[54],"off-policy":[55],"Q-learning":[56],"that":[57,88,109],"do":[58],"not":[59],"scale":[60],"well":[61],"as":[62],"cornerstone,":[64],"with":[65,76],"restricted":[66],"success.":[67],"paper":[69],"studies":[70],"on-policy":[71],"modifications":[72],"algorithms,":[75],"promise":[78],"scalability":[80],"and":[81],"efficiency.":[82],"In":[83],"particular,":[84],"proven":[87],"these":[89],"hybrid":[90],"techniques":[91,112],"guaranteed":[93],"to":[94,96],"converge":[95],"their":[97],"desired":[98],"fixed":[99],"points":[100],"under":[101],"some":[102,127],"restrictions.":[103],"It":[104],"shown,":[107],"experimentally,":[108],"new":[111],"can":[113],"learn":[114],"(from":[115],"self-play)":[116,125],"better":[117],"policies":[118],"previous":[121],"algorithms":[122],"(also":[123],"during":[126],"phases":[128],"exploration.":[131]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}