{"id":"https://openalex.org/W89123072","doi":null,"title":"Stochastic Direct Reinforcement: Application to Simple Games with Recurrence.","display_name":"Stochastic Direct Reinforcement: Application to Simple Games with Recurrence.","alternate_titles":[],"publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W89123072","mag":"89123072"},"language":"en","primary_location":{"id":"mag:89123072","doi":null,"is_oa":false,"landing_page_url":"http://www.icsi.berkeley.edu/pubs/algorithms/stochasticdirect04.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},"parent_works":[],"lineage":["https://openalex.org/W89123072"],"child_works_count":0,"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":"https://openalex.org/A5056861449","display_name":"John E. Moody","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"John Moody","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376614","display_name":"Yufeng Liu","orcid":"https://orcid.org/0000-0002-1686-0545","observed_orcids":["https://orcid.org/0000-0002-1686-0545","https://orcid.org/0009-0002-9107-4859"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Yufeng Liu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1686-0545","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073841545","display_name":"Matthew Saffell","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Matthew Saffell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049793936","display_name":"Kyoungju Youn","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Kyoungju Youn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2991,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.77754789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"34"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9868000149726868,"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":0.9868000149726868,"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/T11031","display_name":"Game Theory and Applications","score":0.005900000222027302,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.002899999963119626,"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/recurrent-reinforcement-learning","display_name":"recurrent reinforcement learning","score":0.9279999732971191},{"id":"https://openalex.org/keywords/stochastic-policies","display_name":"stochastic policies","score":0.8029999732971191},{"id":"https://openalex.org/keywords/multi-agent-interaction","display_name":"multi-agent interaction","score":0.6520000100135803},{"id":"https://openalex.org/keywords/rock-paper-scissors","display_name":"rock-paper-scissors","score":0.7770000100135803},{"id":"https://openalex.org/keywords/iterated-prisoner-s-dilemma","display_name":"iterated prisoner's dilemma","score":0.921999990940094},{"id":"https://openalex.org/keywords/temporal-credit-assignment","display_name":"temporal credit assignment","score":0.7450000047683716},{"id":"https://openalex.org/keywords/recurrent-memory","display_name":"recurrent memory","score":0.8429999947547913},{"id":"https://openalex.org/keywords/cooperation","display_name":"cooperation","score":0.7160000205039978},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8319302797317505},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6622753143310547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6588418483734131},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6111775636672974},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.606971263885498},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5106924176216125},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49009525775909424},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.4865983724594116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4477420747280121},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.33629274368286133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23114794492721558},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10287389159202576},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"mag:89123072","doi":null,"is_oa":false,"landing_page_url":"http://www.icsi.berkeley.edu/pubs/algorithms/stochasticdirect04.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},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.589.4988","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.589.4988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/Symposia/Fall/2004/FS-04-02/FS04-02-004.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.85.2569","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.2569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/~moody/MoodyLSY_SDR_AAAI_2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1513468570","https://openalex.org/W1514115759","https://openalex.org/W1542941925","https://openalex.org/W1579312135","https://openalex.org/W1594297126","https://openalex.org/W1601974704","https://openalex.org/W1607392272","https://openalex.org/W1977051850","https://openalex.org/W2014748701","https://openalex.org/W2018042870","https://openalex.org/W2053616263","https://openalex.org/W2097498347","https://openalex.org/W2104602264","https://openalex.org/W2119717200","https://openalex.org/W2120327309","https://openalex.org/W2145397675","https://openalex.org/W2159813604","https://openalex.org/W2169015875","https://openalex.org/W2345941287"],"related_works":["https://openalex.org/W2946841987","https://openalex.org/W4394674309","https://openalex.org/W351079865","https://openalex.org/W3037719421","https://openalex.org/W7095697378","https://openalex.org/W4213176411","https://openalex.org/W7099755820","https://openalex.org/W7095626097","https://openalex.org/W202381653","https://openalex.org/W1835254890"],"abstract_inverted_index":{"We":[0,109],"investigate":[1],"repeated":[2],"matrix":[3],"games":[4],"with":[5,82,175],"stochastic":[6,36],"players":[7,113,136],"as":[8],"a":[9,27,180],"microcosm":[10],"for":[11,75,86,105,123],"studying":[12],"dynamic,":[13],"multi-agent":[14],"interactions":[15],"using":[16],"the":[17,100,124,156],"Stochastic":[18],"Direct":[19],"Reinforcement":[20,31],"(SDR)":[21],"policy":[22,47,76,147],"gradient":[23,77],"algorithm.":[24],"SDR":[25,42,81,112,135,164,173],"is":[26],"generalization":[28],"of":[29,102,182],"Recurrent":[30],"Learning":[32],"(RRL)":[33],"that":[34,111,141,162],"supports":[35],"policies.":[37],"Unlike":[38],"other":[39],"RL":[40],"algorithms,":[41],"and":[43,97,117,137,144],"RRL":[44],"use":[45,101],"recurrent":[46,57,69,103,142,146,176],"gradients":[48,148,177],"to":[49,66,168],"properly":[50],"address":[51],"temporal":[52],"credit":[53],"assignment":[54],"resulting":[55],"from":[56,71,92],"structure.":[58],"Our":[59],"main":[60],"goals":[61],"in":[62],"this":[63],"paper":[64],"are":[65],"(1)":[67],"distinguish":[68,90],"memory":[70,74],"standard,":[72],"non-recurrent":[73,153,163],"RL,":[78],"(2)":[79],"compare":[80],"Q-type":[83,121],"learning":[84,104],"methods":[85],"simple":[87,125],"games,":[88],"(3)":[89],"reactive":[91],"endogenous":[93],"dynamical":[94],"agent":[95],"behavior":[96],"(4)":[98],"explore":[99],"interacting,":[106],"dynamic":[107,134],"agents.":[108],"find":[110],"learn":[114,166,179],"much":[115],"faster":[116],"hence":[118],"outperform":[119],"recently-proposed":[120],"learners":[122],"game":[126],"Rock,":[127],"Paper,":[128],"Scissors":[129],"(RPS).":[130],"With":[131],"more":[132],"complex,":[133],"opponents,":[138],"we":[139,160],"demonstrate":[140],"representations":[143],"SDR\u2019s":[145],"yield":[149],"better":[150],"performance":[151],"than":[152],"players.":[154],"For":[155],"Iterated":[157],"Prisoners":[158],"Dilemma,":[159],"show":[161],"agents":[165,174],"only":[167],"defect":[169],"(Nash":[170],"equilibrium),":[171],"while":[172],"can":[178],"variety":[181],"interesting":[183],"behaviors,":[184],"including":[185],"cooperation.":[186],"1":[187]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W89123072","counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
