{"id":"https://openalex.org/W4402915306","doi":"https://doi.org/10.1109/mis.2024.3469574","title":"A Q-learning Novelty Search Strategy for Evaluating Robustness of Deep Reinforcement Learning in Open-world Environments","display_name":"A Q-learning Novelty Search Strategy for Evaluating Robustness of Deep Reinforcement Learning in Open-world Environments","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402915306","doi":"https://doi.org/10.1109/mis.2024.3469574"},"language":"en","primary_location":{"id":"doi:10.1109/mis.2024.3469574","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mis.2024.3469574","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Systems","raw_type":"journal-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/A5078188257","display_name":"Shafkat Islam","orcid":"https://orcid.org/0000-0002-8524-2855"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shafkat Islam","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050297425","display_name":"Min\u2013Hsueh Chiu","orcid":"https://orcid.org/0000-0003-0637-7856"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min-Hsueh Chiu","raw_affiliation_strings":["University of Southern California/ISI, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California/ISI, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049482803","display_name":"Trevor Bonjour","orcid":"https://orcid.org/0000-0001-5050-0220"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Bonjour","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045749493","display_name":"Ruy de Oliveira","orcid":"https://orcid.org/0009-0004-4502-8557"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruy de Oliveira","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077320731","display_name":"Bharat Bhargava","orcid":"https://orcid.org/0000-0003-3803-8672"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bharat Bhargava","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074197492","display_name":"Mayank Kejriwal","orcid":"https://orcid.org/0000-0001-5988-8305"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mayank Kejriwal","raw_affiliation_strings":["University of Southern California/ISI, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California/ISI, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5078188257"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14420667,"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":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9057000279426575,"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":0.9057000279426575,"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":0.8496958017349243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8046457171440125},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.800625205039978},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7485758662223816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6409029960632324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5554962158203125}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8496958017349243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046457171440125},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.800625205039978},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7485758662223816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6409029960632324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5554962158203125},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mis.2024.3469574","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mis.2024.3469574","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Despite":[0],"substantial":[1],"progress":[2],"in":[3,18,139],"deep":[4,110],"reinforcement":[5],"learning":[6],"(DRL),":[7],"a":[8,102,109,129,134,140],"systematic":[9],"characterization":[10],"of":[11,41,70,75,137],"DRL":[12,42,130],"agents\u2019":[13],"robustness":[14],"to":[15,46,90],"unexpected":[16,25],"events":[17,26],"the":[19,39,71,73,97],"environment":[20,144],"is":[21,88],"relatively":[22],"understudied.":[23],"Such":[24],"(\u201cnovelties\u201d),":[27],"especially":[28],"those":[29],"that":[30,93,115],"are":[31],"more":[32],"structural":[33],"than":[34],"parametric,":[35],"may":[36],"significantly":[37],"deteriorate":[38],"performance":[40,61],"agents,":[43],"leading":[44],"them":[45],"be":[47,79],"unfit":[48],"for":[49,104],"open-world":[50],"environments":[51],"and":[52,67,107,117],"applications.":[53],"However,":[54],"not":[55],"all":[56,76],"novelties":[57,77,92,123],"affect":[58,96],"an":[59,84],"agent\u2019s":[60],"equally.":[62],"Unfortunately,":[63],"even":[64],"with":[65,124,146],"reasonable":[66],"constrained":[68],"definitions":[69],"problem,":[72],"space":[74],"can":[78,94],"(at":[80],"least)":[81],"exponential.":[82],"Hence,":[83],"effective":[85],"search":[86,113],"strategy":[87,114],"required":[89],"find":[91],"adversely":[95],"agent.":[98,131],"This":[99],"article":[100],"presents":[101],"formalism":[103],"this":[105],"problem":[106],"proposes":[108],"Q-learning-based":[111],"novelty":[112],"efficiently":[116],"systematically":[118],"finds":[119],"candidate":[120],"(potentially":[121],"complex)":[122],"significant":[125],"negative":[126],"impact":[127],"on":[128],"We":[132],"conduct":[133],"detailed":[135],"set":[136],"experiments":[138],"stochastic":[141],"multiagent":[142],"game":[143],"(Monopoly)":[145],"complex":[147],"decision-making":[148],"properties.":[149]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
