{"id":"https://openalex.org/W2091713355","doi":"https://doi.org/10.1177/1059712306072334","title":"Reactivity and Safe Learning in Multi-Agent Systems","display_name":"Reactivity and Safe Learning in Multi-Agent Systems","publication_year":2006,"publication_date":"2006-11-08","ids":{"openalex":"https://openalex.org/W2091713355","doi":"https://doi.org/10.1177/1059712306072334","mag":"2091713355"},"language":"en","primary_location":{"id":"doi:10.1177/1059712306072334","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712306072334","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","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":true,"raw_author_name":"Bikramjit Banerjee","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Tulane                         University, New Orleans, LA 70118, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Tulane                         University, New Orleans, LA 70118, USA,","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101892033","display_name":"Jing Peng","orcid":"https://orcid.org/0000-0001-8822-310X"},"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":["Department of Electrical Engineering and Computer Science, Tulane                         University, New Orleans, LA 70118, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Tulane                         University, New Orleans, LA 70118, USA","institution_ids":["https://openalex.org/I114832834"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5025954824"],"corresponding_institution_ids":["https://openalex.org/I114832834"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18131474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":"4","first_page":"339","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9973000288009644,"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"}},"topics":[{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9973000288009644,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9900000095367432,"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/computer-science","display_name":"Computer science","score":0.825099766254425},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.77303147315979},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7059980630874634},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6229963898658752},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6014435887336731},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5275475382804871},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5219380855560303},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4750542640686035},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.46437492966651917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4461643099784851},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44089144468307495},{"id":"https://openalex.org/keywords/reactivity","display_name":"Reactivity (psychology)","score":0.42583024501800537},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4055430293083191},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34658539295196533},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3230515420436859},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3124126195907593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.825099766254425},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.77303147315979},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7059980630874634},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6229963898658752},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6014435887336731},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5275475382804871},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5219380855560303},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4750542640686035},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.46437492966651917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4461643099784851},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44089144468307495},{"id":"https://openalex.org/C2776910235","wikidata":"https://www.wikidata.org/wiki/Q18574","display_name":"Reactivity (psychology)","level":3,"score":0.42583024501800537},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4055430293083191},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34658539295196533},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3230515420436859},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3124126195907593},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/1059712306072334","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712306072334","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.857.9442","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.857.9442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://adb.sagepub.com/content/14/4/339.full.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.3975","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.3975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://adb.sagepub.com/cgi/reprint/14/4/339.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1481781224","https://openalex.org/W1513468570","https://openalex.org/W1542941925","https://openalex.org/W1576718874","https://openalex.org/W1583837637","https://openalex.org/W1587589241","https://openalex.org/W1589674068","https://openalex.org/W1607392272","https://openalex.org/W1665423881","https://openalex.org/W1812360833","https://openalex.org/W1979025384","https://openalex.org/W2038557026","https://openalex.org/W2104602264","https://openalex.org/W2106887613","https://openalex.org/W2116067849","https://openalex.org/W2120327309","https://openalex.org/W2132260710","https://openalex.org/W2134112261","https://openalex.org/W2138362680","https://openalex.org/W2148496763","https://openalex.org/W2152267087","https://openalex.org/W2155027007","https://openalex.org/W2168281471","https://openalex.org/W2171863654","https://openalex.org/W2330024298","https://openalex.org/W2492794003","https://openalex.org/W2595697910","https://openalex.org/W2999905431","https://openalex.org/W3101518876","https://openalex.org/W4230665353","https://openalex.org/W4234761190"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2,32],"(MRL)":[3],"is":[4,15],"a":[5,92,159],"growing":[6],"area":[7],"of":[8,50,63,74,79,89,91,118,124],"research.":[9],"What":[10],"makes":[11],"it":[12],"particularly":[13],"challenging":[14],"that":[16,134,140,148],"multiple":[17],"learners":[18,35],"render":[19],"each":[20],"other's":[21],"environments":[22],"non-stationary.":[23],"In":[24,59],"addition":[25],"to":[26,30,46,101,127,151,163,175,184],"adapting":[27],"their":[28,41,129],"behaviors":[29],"other":[31],"agents,":[33],"online":[34,42,77],"must":[36,155],"also":[37,146],"provide":[38],"assurances":[39],"about":[40],"performance":[43,78],"in":[44,55,76,121],"order":[45],"promote":[47],"user":[48],"trust":[49],"adaptive":[51,168],"agent":[52],"systems":[53],"deployed":[54],"real":[56],"world":[57],"applications.":[58],"this":[60,116],"article,":[61],"instead":[62],"developing":[64],"new":[65],"algorithms":[66,126],"with":[67,161],"such":[68],"assurances,":[69],"we":[70],"study":[71],"the":[72,86,122,177],"question":[73],"safety":[75,179],"some":[80,103],"existing":[81],"MRL":[82],"algorithms.":[83],"We":[84,112,132,145],"identify":[85],"key":[87],"notion":[88],"reactivity":[90,154],"learner":[93,136],"by":[94,110],"analyzing":[95],"how":[96],"an":[97,167],"algorithm":[98],"(PHC-Exploiter),":[99],"designed":[100,139,174],"exploit":[102],"simpler":[104],"opponents,":[105],"can":[106,137,141],"itself":[107],"be":[108,138],"exploited":[109],"them.":[111],"quantify":[113],"and":[114,165,180],"analyze":[115],"concept":[117],"reac":[119],"tivity":[120],"context":[123],"these":[125],"explain":[128],"experimental":[130],"behaviors.":[131],"argue":[133],"no":[135],"deliberately":[142],"avoid":[143],"exploitation.":[144],"show":[147],"any":[149],"attempt":[150],"opti":[152],"mize":[153],"take":[156],"into":[157],"account":[158],"tradeoff":[160],"sensitivity":[162,183],"noise,":[164],"devise":[166],"method":[169],"(based":[170],"on":[171],"environmental":[172],"feedback)":[173],"maximize":[176],"learner's":[178],"minimize":[181],"its":[182],"noise.":[185]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}