{"id":"https://openalex.org/W3207211154","doi":"https://doi.org/10.1109/smartcomp52413.2021.00081","title":"Mutual Reinforcement Learning with Heterogenous Agents","display_name":"Mutual Reinforcement Learning with Heterogenous Agents","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3207211154","doi":"https://doi.org/10.1109/smartcomp52413.2021.00081","mag":"3207211154"},"language":"en","primary_location":{"id":"doi:10.1109/smartcomp52413.2021.00081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smartcomp52413.2021.00081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Smart Computing (SMARTCOMP)","raw_type":"proceedings-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/A5065517173","display_name":"Cameron Reid","orcid":null},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cameron Reid","raw_affiliation_strings":["School of Computer and Information Science, Indiana University Purdue University Indianapolis, Indianapolis, Indiana"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Indiana University Purdue University Indianapolis, Indianapolis, Indiana","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106085532","display_name":"Snehasis Mukhopadhyay","orcid":null},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Snehasis Mukhopadhyay","raw_affiliation_strings":["School of Computer and Information Science, Indiana University Purdue University Indianapolis, Indianapolis, Indiana"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Indiana University Purdue University Indianapolis, Indianapolis, Indiana","institution_ids":["https://openalex.org/I55769427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065517173"],"corresponding_institution_ids":["https://openalex.org/I55769427"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63956065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"395","last_page":"397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9226999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8896976709365845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8207747936248779},{"id":"https://openalex.org/keywords/negotiation","display_name":"Negotiation","score":0.6419641971588135},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.5467005968093872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5421889424324036},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48994630575180054},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41029679775238037}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8896976709365845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207747936248779},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.6419641971588135},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.5467005968093872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5421889424324036},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48994630575180054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41029679775238037},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smartcomp52413.2021.00081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smartcomp52413.2021.00081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Smart Computing (SMARTCOMP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2091565802","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2620645529","https://openalex.org/W2620998106","https://openalex.org/W2970971581","https://openalex.org/W3132794238","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6766978945","https://openalex.org/W6791081780"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W2786230833","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344"],"abstract_inverted_index":{"Mutual":[0],"learning":[1,27,34,85],"is":[2],"an":[3,40],"emerging":[4],"technique":[5],"for":[6],"allowing":[7],"intelligent":[8],"systems":[9,29],"to":[10,17,55],"learn":[11],"from":[12,72],"each":[13],"other,":[14],"giving":[15],"rise":[16],"improved":[18],"performance.":[19],"In":[20,36],"this":[21,82],"paper,":[22],"we":[23,38,76],"explore":[24],"mutual":[25],"reinforcement":[26],"between":[28],"which":[30,42],"use":[31],"very":[32],"different":[33],"algorithms.":[35],"particular,":[37],"present":[39,77],"algorithm":[41],"allows":[43],"two":[44],"agents,":[45,74],"one":[46],"using":[47,51],"Q-learning":[48],"and":[49,75],"another":[50],"adaptive":[52],"dynamic":[53],"programming,":[54],"share":[56],"learned":[57],"knowledge.":[58],"We":[59],"discuss":[60],"how":[61,81],"these":[62],"agents":[63],"negotiate":[64],"the":[65,84],"relative":[66],"importance":[67],"of":[68],"knowledge":[69],"they":[70],"receive":[71],"other":[73],"results":[78],"that":[79],"show":[80],"affects":[83],"process.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}