{"id":"https://openalex.org/W4400727628","doi":"https://doi.org/10.1109/rose62198.2024.10590850","title":"A Model-Free Solution for Stackelberg Games Using Reinforcement Learning and Projection Approaches","display_name":"A Model-Free Solution for Stackelberg Games Using Reinforcement Learning and Projection Approaches","publication_year":2024,"publication_date":"2024-06-20","ids":{"openalex":"https://openalex.org/W4400727628","doi":"https://doi.org/10.1109/rose62198.2024.10590850"},"language":"en","primary_location":{"id":"doi:10.1109/rose62198.2024.10590850","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rose62198.2024.10590850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Robotic and Sensors Environments (ROSE)","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/A5045456375","display_name":"Mohammed Abouheaf","orcid":"https://orcid.org/0000-0002-6130-9015"},"institutions":[{"id":"https://openalex.org/I157417397","display_name":"Bowling Green State University","ror":"https://ror.org/00ay7va13","country_code":"US","type":"education","lineage":["https://openalex.org/I157417397"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammed Abouheaf","raw_affiliation_strings":["Robotics Engineering, Bowling Green State University,Bowling Green,OH,USA,43403"],"affiliations":[{"raw_affiliation_string":"Robotics Engineering, Bowling Green State University,Bowling Green,OH,USA,43403","institution_ids":["https://openalex.org/I157417397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036560577","display_name":"Wail Gueaieb","orcid":"https://orcid.org/0000-0001-6490-4648"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wail Gueaieb","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, University of Ottawa,Ottawa,Ontario,Canada,K1N 6N5"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, University of Ottawa,Ottawa,Ontario,Canada,K1N 6N5","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000681023","display_name":"Suruz Miah","orcid":"https://orcid.org/0000-0001-6533-0770"},"institutions":[{"id":"https://openalex.org/I24648388","display_name":"Bradley University","ror":"https://ror.org/04kmeaw70","country_code":"US","type":"education","lineage":["https://openalex.org/I24648388"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suruz Miah","raw_affiliation_strings":["Bradley University,Department of Electrical and Computer Engineering,Peoria,Illinois,USA,61615"],"affiliations":[{"raw_affiliation_string":"Bradley University,Department of Electrical and Computer Engineering,Peoria,Illinois,USA,61615","institution_ids":["https://openalex.org/I24648388"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004105318","display_name":"Esam H. Abdelhameed","orcid":"https://orcid.org/0000-0001-8208-580X"},"institutions":[{"id":"https://openalex.org/I86310350","display_name":"Aswan University","ror":"https://ror.org/048qnr849","country_code":"EG","type":"education","lineage":["https://openalex.org/I86310350"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Esam H. Abdelhameed","raw_affiliation_strings":["Aswan University,Faculty of Energy Engineering,Aswan,Egypt,81528"],"affiliations":[{"raw_affiliation_string":"Aswan University,Faculty of Energy Engineering,Aswan,Egypt,81528","institution_ids":["https://openalex.org/I86310350"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045456375"],"corresponding_institution_ids":["https://openalex.org/I157417397"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10940335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.7767000198364258,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.7767000198364258,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7749999761581421,"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/T10067","display_name":"Stochastic processes and financial applications","score":0.6657999753952026,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stackelberg-competition","display_name":"Stackelberg competition","score":0.9354969263076782},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7699331045150757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6663097739219666},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.6031931638717651},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.407120943069458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.343024879693985},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.2387526035308838},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17308050394058228},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12094250321388245}],"concepts":[{"id":"https://openalex.org/C199510392","wikidata":"https://www.wikidata.org/wiki/Q1184602","display_name":"Stackelberg competition","level":2,"score":0.9354969263076782},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7699331045150757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6663097739219666},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.6031931638717651},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.407120943069458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.343024879693985},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2387526035308838},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17308050394058228},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12094250321388245}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rose62198.2024.10590850","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rose62198.2024.10590850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Robotic and Sensors Environments (ROSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1984986877","https://openalex.org/W1986253301","https://openalex.org/W1990005421","https://openalex.org/W2005437559","https://openalex.org/W2013460950","https://openalex.org/W2033209357","https://openalex.org/W2039354440","https://openalex.org/W2084202551","https://openalex.org/W2086977346","https://openalex.org/W2090804924","https://openalex.org/W2484646121","https://openalex.org/W2503416842","https://openalex.org/W2972364442","https://openalex.org/W3046896135","https://openalex.org/W3084618952","https://openalex.org/W3089490373","https://openalex.org/W3120441334","https://openalex.org/W3125172959","https://openalex.org/W3129762550","https://openalex.org/W3131254153","https://openalex.org/W3156359084","https://openalex.org/W3159667783","https://openalex.org/W3164978030","https://openalex.org/W3189366299","https://openalex.org/W3190755268","https://openalex.org/W3207446171","https://openalex.org/W3210713039","https://openalex.org/W4205326910","https://openalex.org/W4206037914","https://openalex.org/W4206073426","https://openalex.org/W4226309445","https://openalex.org/W4250606304","https://openalex.org/W4280580045","https://openalex.org/W4313886730","https://openalex.org/W4319453072","https://openalex.org/W4324125522","https://openalex.org/W4324137886","https://openalex.org/W4361026739","https://openalex.org/W4386524614","https://openalex.org/W4386883865","https://openalex.org/W4390578067","https://openalex.org/W4392798814","https://openalex.org/W4393204026","https://openalex.org/W4393397186"],"related_works":["https://openalex.org/W1987562536","https://openalex.org/W4383533535","https://openalex.org/W2375814310","https://openalex.org/W4255938919","https://openalex.org/W2903244929","https://openalex.org/W4380353856","https://openalex.org/W2347216446","https://openalex.org/W1995212308","https://openalex.org/W2364137969","https://openalex.org/W2321381430"],"abstract_inverted_index":{"The":[0,20,74,92],"Stackelberg":[1,47],"game":[2,48],"is":[3,117],"adopted":[4],"in":[5,34,49,66],"many":[6],"robotics":[7],"applications.":[8],"It":[9],"features":[10],"a":[11,17,35,41,95,107],"dynamic":[12],"multi-player":[13],"setup":[14],"based":[15],"on":[16,119],"leader-follower":[18],"structure.":[19],"main":[21],"challenge":[22],"involves":[23],"implementing":[24],"model-free":[25,42],"strategies":[26,63],"that":[27],"can":[28],"effectively":[29],"respond":[30],"to":[31,110,126],"unstructured":[32,124],"environments":[33],"data-driven":[36],"manner.":[37],"This":[38,115],"paper":[39],"presents":[40],"method":[43,93,109],"for":[44],"solving":[45],"the":[46,52,58,62,71,85,101],"real-time,":[50],"wherein":[51],"follower's":[53],"strategy":[54],"assumes":[55],"knowledge":[56,69],"of":[57,70],"leader's":[59],"tactics.":[60],"Moreover,":[61],"are":[64,77,104],"implemented":[65],"real-time":[67],"without":[68],"players'":[72],"dynamics.":[73],"optimization":[75],"goals":[76],"expressed":[78],"through":[79],"coupled":[80],"Bellman":[81],"optimality":[82],"equations,":[83],"highlighting":[84],"dependency":[86],"between":[87],"leader":[88],"and":[89,113,123],"follower":[90],"strategies.":[91],"utilizes":[94],"linear":[96],"adaptive":[97],"critics":[98],"framework,":[99],"where":[100],"actor-critic":[102],"weights":[103],"adjusted":[105],"using":[106],"projection":[108],"ensure":[111],"stability":[112],"convergence.":[114],"approach":[116],"evaluated":[118],"systems":[120],"with":[121],"delays":[122],"disturbances":[125],"demonstrate":[127],"its":[128],"robustness.":[129]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}