{"id":"https://openalex.org/W3187324823","doi":"https://doi.org/10.1109/smc52423.2021.9658704","title":"Inverse Reinforcement Learning for Strategy Identification","display_name":"Inverse Reinforcement Learning for Strategy Identification","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3187324823","doi":"https://doi.org/10.1109/smc52423.2021.9658704","mag":"3187324823"},"language":"en","primary_location":{"id":"doi:10.1109/smc52423.2021.9658704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658704","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5023688216","display_name":"Mark Rucker","orcid":"https://orcid.org/0000-0003-0705-6704"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Rucker","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060460337","display_name":"Stephen Adams","orcid":"https://orcid.org/0000-0002-1207-4504"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Adams","raw_affiliation_strings":["Hume Center for National Defense and Technology, Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hume Center for National Defense and Technology, Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056474827","display_name":"Roy Hayes","orcid":"https://orcid.org/0000-0002-9696-0000"},"institutions":[{"id":"https://openalex.org/I4210116219","display_name":"Engineering Systems (United States)","ror":"https://ror.org/02qg60849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roy Hayes","raw_affiliation_strings":["CTO of Systems Engineering, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CTO of Systems Engineering, Inc","institution_ids":["https://openalex.org/I4210116219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056670558","display_name":"Peter A. Beling","orcid":"https://orcid.org/0000-0003-2196-6982"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter A. Beling","raw_affiliation_strings":["Intelligent Systems Lab in Hume Center for National Security and Technology","Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Lab in Hume Center for National Security and Technology","institution_ids":[]},{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3067","last_page":"3074"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9887999892234802,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.984000027179718,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6947611570358276},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6284278631210327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6187320351600647},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5211051106452942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.477989137172699},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3891880512237549},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1838046908378601},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07460987567901611}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6947611570358276},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6284278631210327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187320351600647},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5211051106452942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.477989137172699},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3891880512237549},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1838046908378601},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07460987567901611},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc52423.2021.9658704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658704","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W28373771","https://openalex.org/W41554520","https://openalex.org/W1999874108","https://openalex.org/W2025423725","https://openalex.org/W2051828847","https://openalex.org/W2061562262","https://openalex.org/W2096871511","https://openalex.org/W2098774185","https://openalex.org/W2113913482","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2144445939","https://openalex.org/W2169209873","https://openalex.org/W2226344442","https://openalex.org/W2227909145","https://openalex.org/W2246008130","https://openalex.org/W2397891592","https://openalex.org/W2573645042","https://openalex.org/W2744369598","https://openalex.org/W2781623365","https://openalex.org/W2783366778","https://openalex.org/W2788730383","https://openalex.org/W2789386227","https://openalex.org/W2791590003","https://openalex.org/W2811409798","https://openalex.org/W2886446163","https://openalex.org/W2909906617","https://openalex.org/W2949206666","https://openalex.org/W2949693231","https://openalex.org/W2980903217","https://openalex.org/W3007758655","https://openalex.org/W4237193969","https://openalex.org/W6674884181","https://openalex.org/W6685331716","https://openalex.org/W6689267661","https://openalex.org/W6691047812","https://openalex.org/W6731984678","https://openalex.org/W6773993933"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0],"adversarial":[1,71],"environments,":[2],"one":[3,28],"side":[4],"could":[5,29],"gain":[6],"an":[7,20,40],"advantage":[8],"by":[9],"identifying":[10],"the":[11,35,74,81,97,111],"opponent\u2019s":[12,21,36,41],"strategy.":[13],"For":[14],"example,":[15],"in":[16,70],"combat":[17,88],"games,":[18],"if":[19],"strategy":[22,42,104],"is":[23,43],"identified":[24,116],"as":[25],"overly":[26],"aggressive,":[27],"lay":[30],"a":[31,118],"trap":[32],"that":[33,110],"exploits":[34],"aggressive":[37],"nature.":[38],"However,":[39],"not":[44],"always":[45],"apparent":[46],"and":[47,95,127],"may":[48],"need":[49],"to":[50,61,67,102],"be":[51,115],"estimated":[52],"from":[53,91],"observations":[54],"of":[55,76,83,120],"their":[56],"actions.":[57],"This":[58],"paper":[59],"proposes":[60],"use":[62],"inverse":[63],"reinforcement":[64],"learning":[65],"(IRL)":[66],"identify":[68],"strategies":[69,94],"environments.":[72],"Specifically,":[73],"contributions":[75],"this":[77,84],"work":[78],"are":[79],"1)":[80],"demonstration":[82],"concept":[85],"on":[86],"gaming":[87],"data":[89],"generated":[90],"three":[92],"pre-defined":[93],"2)":[96],"framework":[98],"for":[99],"using":[100,117],"IRL":[101],"achieve":[103],"identification.":[105],"The":[106],"numerical":[107],"experiments":[108],"demonstrate":[109],"recovered":[112],"rewards":[113],"can":[114],"variety":[119],"techniques":[121],"including":[122],"visual":[123],"analysis,":[124,126],"cluster":[125],"supervised":[128],"classification.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}