{"id":"https://openalex.org/W3118463161","doi":"https://doi.org/10.1109/cdc42340.2020.9303995","title":"A Meta-Learning and Bounded Rationality Framework for Repeated Games in Adversarial Environments","display_name":"A Meta-Learning and Bounded Rationality Framework for Repeated Games in Adversarial Environments","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3118463161","doi":"https://doi.org/10.1109/cdc42340.2020.9303995","mag":"3118463161"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9303995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","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/A5058970736","display_name":"Aris Kanellopoulos","orcid":"https://orcid.org/0000-0001-5983-0875"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aris Kanellopoulos","raw_affiliation_strings":["Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068923749","display_name":"Filippos Fotiadis","orcid":"https://orcid.org/0000-0002-9239-3387"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Filippos Fotiadis","raw_affiliation_strings":["Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024301984","display_name":"Vijay Gupta","orcid":"https://orcid.org/0000-0001-7060-3956"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Gupta","raw_affiliation_strings":["University of Notre, Dame, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre, Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2608,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65481506,"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":"1640","last_page":"1645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9962999820709229,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9764999747276306,"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/computer-science","display_name":"Computer science","score":0.7209818363189697},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7134618163108826},{"id":"https://openalex.org/keywords/bounded-rationality","display_name":"Bounded rationality","score":0.6554809808731079},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6074544191360474},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5831231474876404},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5797206163406372},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5708795189857483},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5310051441192627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5046647787094116},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.4667147994041443},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.4555143713951111},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.4541546404361725},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3568040132522583},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.355231910943985},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3509123623371124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20391646027565002},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.15931111574172974},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1584392786026001},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15324535965919495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209818363189697},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7134618163108826},{"id":"https://openalex.org/C58694771","wikidata":"https://www.wikidata.org/wiki/Q814385","display_name":"Bounded rationality","level":2,"score":0.6554809808731079},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6074544191360474},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5831231474876404},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5797206163406372},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5708795189857483},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5310051441192627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5046647787094116},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.4667147994041443},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4555143713951111},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.4541546404361725},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3568040132522583},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.355231910943985},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3509123623371124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20391646027565002},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.15931111574172974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1584392786026001},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15324535965919495},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc42340.2020.9303995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W357005916","https://openalex.org/W601351931","https://openalex.org/W1531590217","https://openalex.org/W1578630563","https://openalex.org/W1581842928","https://openalex.org/W1592657892","https://openalex.org/W1605188341","https://openalex.org/W1713503745","https://openalex.org/W1983523797","https://openalex.org/W1988613094","https://openalex.org/W2034743631","https://openalex.org/W2036837037","https://openalex.org/W2068869385","https://openalex.org/W2100994411","https://openalex.org/W2120586058","https://openalex.org/W2131030156","https://openalex.org/W2150355110","https://openalex.org/W2172060758","https://openalex.org/W2510037087","https://openalex.org/W2727450595","https://openalex.org/W2794929787","https://openalex.org/W2917721237","https://openalex.org/W2962676888","https://openalex.org/W2962941560","https://openalex.org/W2969210610","https://openalex.org/W3106491339","https://openalex.org/W4211108990","https://openalex.org/W4238729853","https://openalex.org/W6647328502","https://openalex.org/W6743783142","https://openalex.org/W6767560639","https://openalex.org/W6786583451"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W3121383024"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"a":[3,22,97,106],"meta-learning":[4],"framework":[5,75],"for":[6],"games":[7],"between":[8],"adapting":[9],"players":[10,103],"is":[11,19,39,86],"proposed.":[12],"An":[13],"agent":[14],"with":[15,21],"increased":[16],"cognitive":[17],"abilities":[18],"augmented":[20],"structure":[23],"that":[24,31,43,56,81],"allows":[25],"them":[26],"to":[27,96],"identify":[28],"the":[29,36,52,59,62,68,74,84,94,111],"way":[30],"their":[32],"opponents":[33,63],"learn":[34],"during":[35],"game.":[37],"This":[38],"achieved":[40],"via":[41,76],"approximators":[42],"are":[44],"tuned":[45],"online":[46],"leveraging":[47],"only":[48],"observed":[49],"actions":[50],"from":[51],"environment.":[53],"We":[54],"show":[55,91],"knowledge":[57,82],"of":[58,61,67,83,93,102,113],"utilities":[60,85],"enable":[64],"asymptotic":[65],"convergence":[66,92],"approximation":[69],"weights.":[70],"We,":[71],"then,":[72],"extend":[73],"backpropagation":[77],"through":[78],"time":[79],"such":[80],"not":[87],"necessary":[88],"and":[89],"we":[90],"errors":[95],"residual":[98],"set.":[99],"Finally,":[100],"simulations":[101],"learning":[104],"in":[105],"penny":[107],"matching":[108],"game":[109],"demonstrate":[110],"efficacy":[112],"our":[114],"approach.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}