{"id":"https://openalex.org/W2948939059","doi":"https://doi.org/10.48550/arxiv.1906.01119","title":"Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE)","display_name":"Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE)","publication_year":2019,"publication_date":"2019-06-03","ids":{"openalex":"https://openalex.org/W2948939059","doi":"https://doi.org/10.48550/arxiv.1906.01119","mag":"2948939059"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1906.01119","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01119","pdf_url":"https://arxiv.org/pdf/1906.01119","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.01119","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062734917","display_name":"Vahid Behzadan","orcid":"https://orcid.org/0000-0002-6229-9365","observed_orcids":["https://orcid.org/0000-0002-6229-9365"]},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Behzadan, Vahid","raw_affiliation_strings":["Kansas State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kansas State University","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016291944","display_name":"William W.Y. Hsu","orcid":"https://orcid.org/0000-0002-5168-070X","observed_orcids":["https://orcid.org/0000-0002-5168-070X"]},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsu, William","raw_affiliation_strings":["Kansas State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kansas State University","institution_ids":["https://openalex.org/I189590672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189590672"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9829000234603882,"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":0.9829000234603882,"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":0.01549999974668026,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.00019999999494757503,"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/adversarial-training","display_name":"adversarial training","score":0.9959999918937683},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.8550000190734863},{"id":"https://openalex.org/keywords/adversarial-robustness","display_name":"adversarial robustness","score":0.8090000152587891},{"id":"https://openalex.org/keywords/exploration-strategy","display_name":"exploration strategy","score":0.7049999833106995},{"id":"https://openalex.org/keywords/epsilon-greedy","display_name":"epsilon-greedy","score":0.7580000162124634},{"id":"https://openalex.org/keywords/boltzmann-exploration","display_name":"Boltzmann exploration","score":0.9990000128746033},{"id":"https://openalex.org/keywords/sample-inefficiency","display_name":"sample inefficiency","score":0.8519999980926514},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7620000243186951}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8632621169090271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4469107389450073},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3645239472389221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3135016858577728}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1906.01119","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01119","pdf_url":"https://arxiv.org/pdf/1906.01119","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1906.01119","doi":"https://doi.org/10.48550/arxiv.1906.01119","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.01119","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.01119","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01119","pdf_url":"https://arxiv.org/pdf/1906.01119","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948939059.pdf","grobid_xml":"https://content.openalex.org/works/W2948939059.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2269778407","https://openalex.org/W2602963933","https://openalex.org/W2724169821","https://openalex.org/W2775998942","https://openalex.org/W2809668646","https://openalex.org/W2896016186","https://openalex.org/W2962749646","https://openalex.org/W2963099933","https://openalex.org/W2964108292"],"related_works":["https://openalex.org/W2775998942","https://openalex.org/W2925106412","https://openalex.org/W2987815066","https://openalex.org/W3011736333","https://openalex.org/W2948471104","https://openalex.org/W4207057521","https://openalex.org/W3209446190","https://openalex.org/W7124247083","https://openalex.org/W2964108292","https://openalex.org/W2883618862"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,10,38,52,73,81,96],"effectiveness":[4],"of":[5,12,26,40,54,72,83,90],"adversarial":[6,27,41,56],"training":[7,28,57],"in":[8,29,93],"enhancing":[9],"robustness":[11],"Deep":[13],"Q-Network":[14],"(DQN)":[15],"policies":[16],"to":[17,37,43],"state-space":[18],"perturbations.":[19],"We":[20,79],"first":[21],"present":[22],"a":[23,61,69],"formal":[24],"analysis":[25],"DQN":[30],"agents":[31],"and":[32,59,76,100],"its":[33,91],"performance":[34,92],"with":[35,95],"respect":[36],"proportion":[39],"perturbations":[42],"nominal":[44],"observations":[45],"used":[46],"for":[47],"training.":[48],"Next,":[49],"we":[50],"consider":[51],"sample-inefficiency":[53],"current":[55],"techniques,":[58],"propose":[60],"novel":[62],"Adversarially-Guided":[63],"Exploration":[64],"(AGE)":[65],"mechanism":[66,86],"based":[67],"on":[68],"modified":[70],"hybrid":[71],"$\u03b5$-greedy":[74,99],"algorithm":[75],"Boltzmann":[77],"exploration.":[78],"verify":[80],"feasibility":[82],"this":[84],"exploration":[85,103],"through":[87],"experimental":[88],"evaluation":[89],"comparison":[94],"traditional":[97],"decaying":[98],"parameter-space":[101],"noise":[102],"algorithms.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-06-14T00:00:00"}