{"id":"https://openalex.org/W4285603252","doi":"https://doi.org/10.24963/ijcai.2022/430","title":"Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training","display_name":"Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285603252","doi":"https://doi.org/10.24963/ijcai.2022/430"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/430","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/430","pdf_url":"https://www.ijcai.org/proceedings/2022/0430.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0430.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074036509","display_name":"Peide Huang","orcid":"https://orcid.org/0000-0001-6108-5069"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peide Huang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102020639","display_name":"Mengdi Xu","orcid":"https://orcid.org/0000-0001-6087-7558"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengdi Xu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061127138","display_name":"Fei Fang","orcid":"https://orcid.org/0000-0003-2256-8329"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Fang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037644321","display_name":"Ding Zhao","orcid":"https://orcid.org/0000-0002-9400-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding Zhao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3099","last_page":"3106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.984499990940094,"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/T11807","display_name":"Infrastructure Resilience and Vulnerability Analysis","score":0.9629999995231628,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stackelberg-competition","display_name":"Stackelberg competition","score":0.9274551272392273},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8590989112854004},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.800388514995575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719565033912659},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.653800904750824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6024695634841919},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.557520866394043},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5364867448806763},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5052452683448792},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4676266312599182},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.44553378224372864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41803276538848877},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.41124871373176575},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12347081303596497},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.08143821358680725},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0759599506855011}],"concepts":[{"id":"https://openalex.org/C199510392","wikidata":"https://www.wikidata.org/wiki/Q1184602","display_name":"Stackelberg competition","level":2,"score":0.9274551272392273},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8590989112854004},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.800388514995575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719565033912659},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.653800904750824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6024695634841919},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.557520866394043},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5364867448806763},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5052452683448792},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4676266312599182},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.44553378224372864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41803276538848877},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.41124871373176575},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12347081303596497},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.08143821358680725},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0759599506855011},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/430","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/430","pdf_url":"https://www.ijcai.org/proceedings/2022/0430.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/430","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/430","pdf_url":"https://www.ijcai.org/proceedings/2022/0430.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G190383499","display_name":"S&AS:FND:COLLAB:Unsupervised Rare Event Learning - With Applications on Autonomous Vehicles","funder_award_id":"1849304","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4321615664","display_name":"CAREER: Integrating Machine Learning with Game Theory for Multiagent Communication and Coordination","funder_award_id":"2046640","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6350943594","display_name":null,"funder_award_id":"CNS-2047454","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6911058591","display_name":null,"funder_award_id":"IIS-2046640","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285603252.pdf","grobid_xml":"https://content.openalex.org/works/W4285603252.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2060727197","https://openalex.org/W2098841537","https://openalex.org/W2105078254","https://openalex.org/W2136058147","https://openalex.org/W2140153041","https://openalex.org/W2602963933","https://openalex.org/W2914994663","https://openalex.org/W2939104739","https://openalex.org/W2981030070","https://openalex.org/W3004473134","https://openalex.org/W3035051902","https://openalex.org/W3035665052","https://openalex.org/W3035723062","https://openalex.org/W3049707075","https://openalex.org/W3100975812","https://openalex.org/W3105149082","https://openalex.org/W3110161557","https://openalex.org/W3120778962","https://openalex.org/W3133276906","https://openalex.org/W3133465684","https://openalex.org/W3154264273","https://openalex.org/W3174920238","https://openalex.org/W4205424143","https://openalex.org/W4287116306","https://openalex.org/W4295150809","https://openalex.org/W4297627396","https://openalex.org/W4302033101","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W4320018150","https://openalex.org/W4239582170","https://openalex.org/W2918664383","https://openalex.org/W106056076","https://openalex.org/W4320855730","https://openalex.org/W2135200719","https://openalex.org/W2976114880","https://openalex.org/W2236801283","https://openalex.org/W2728657731","https://openalex.org/W2328458106"],"abstract_inverted_index":{"Robust":[0,22],"Reinforcement":[1,24],"Learning":[2,25],"(RL)":[3],"focuses":[4],"on":[5],"improving":[6],"performances":[7],"under":[8],"model":[9,91],"errors":[10],"or":[11],"adversarial":[12,133],"attacks,":[13],"which":[14,57,135],"facilitates":[15],"the":[16,30,40,54,60,97,109,118,124,154],"real-life":[17],"deployment":[18],"of":[19,29,39,63,83],"RL":[20,64,85,137],"agents.":[21],"Adversarial":[23],"(RARL)":[26],"is":[27],"one":[28],"most":[31,38],"popular":[32],"frameworks":[33],"for":[34,104],"robust":[35,84,105,139],"RL.":[36],"However,":[37],"existing":[41],"literature":[42],"models":[43],"RARL":[44],"as":[45,53],"a":[46,79,87],"zero-sum":[47],"simultaneous":[48],"game":[49,90],"with":[50],"Nash":[51],"equilibrium":[52],"solution":[55],"concept,":[56],"could":[58],"overlook":[59],"sequential":[61,98],"nature":[62,99],"deployments,":[65],"produce":[66],"overly":[67],"conservative":[68],"agents,":[69],"and":[70,100,147,158],"induce":[71],"training":[72,145],"instability.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77],"introduce":[78],"novel":[80],"hierarchical":[81],"formulation":[82],"--":[86,94],"general-sum":[88],"Stackelberg":[89,110,119],"called":[92],"RRL-Stack":[93],"to":[95,114],"formalize":[96],"provide":[101],"extra":[102],"flexibility":[103],"training.":[106],"We":[107],"develop":[108],"Policy":[111],"Gradient":[112],"algorithm":[113,142],"solve":[115],"RRL-Stack,":[116],"leveraging":[117],"learning":[120],"dynamics":[121],"by":[122],"considering":[123],"adversary's":[125],"response.":[126],"Our":[127,141],"method":[128],"generates":[129],"challenging":[130],"yet":[131],"solvable":[132],"environments":[134],"benefit":[136],"agents'":[138],"learning.":[140],"demonstrates":[143],"better":[144],"stability":[146],"robustness":[148],"against":[149],"different":[150],"testing":[151],"conditions":[152],"in":[153],"single-agent":[155],"robotics":[156],"control":[157],"multi-agent":[159],"highway":[160],"merging":[161],"tasks.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}