{"id":"https://openalex.org/W4399418847","doi":"https://doi.org/10.1145/3651671.3651762","title":"Soft Adversarial Offline Reinforcement Learning via Reducing the Attack Strength for Generalization","display_name":"Soft Adversarial Offline Reinforcement Learning via Reducing the Attack Strength for Generalization","publication_year":2024,"publication_date":"2024-02-02","ids":{"openalex":"https://openalex.org/W4399418847","doi":"https://doi.org/10.1145/3651671.3651762"},"language":"en","primary_location":{"id":"doi:10.1145/3651671.3651762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","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/A5034681877","display_name":"Weijie Qiao","orcid":"https://orcid.org/0009-0007-8158-5248"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wandi Qiao","raw_affiliation_strings":["MIRA Lab, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0007-8158-5248","affiliations":[{"raw_affiliation_string":"MIRA Lab, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057395265","display_name":"Rui Yang","orcid":"https://orcid.org/0009-0004-5137-9302"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yang","raw_affiliation_strings":["MIRA Lab, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0004-5137-9302","affiliations":[{"raw_affiliation_string":"MIRA Lab, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034681877"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06238449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"498","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"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":0.9998000264167786,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9926999807357788,"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":0.9837999939918518,"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-system","display_name":"Adversarial system","score":0.9395582675933838},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7852545380592346},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7518571019172668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7389944195747375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6428405046463013},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5158021450042725},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11170798540115356}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9395582675933838},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7852545380592346},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7518571019172668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7389944195747375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6428405046463013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5158021450042725},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11170798540115356},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3651671.3651762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1587246893","https://openalex.org/W2788862220","https://openalex.org/W2978455699","https://openalex.org/W3033324992","https://openalex.org/W3037440645","https://openalex.org/W3127561923","https://openalex.org/W3152878473","https://openalex.org/W4221141443","https://openalex.org/W6780159193"],"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":{"Improving":[0],"the":[1,24,29,40,60,67,81,85,126,138,153],"generalization":[2,30,69,98,176],"ability":[3,31,70],"in":[4,13,45,71,84,132],"offline":[5,46,90,108,133],"reinforcement":[6],"learning":[7,57,76],"(RL)":[8],"has":[9],"received":[10],"much":[11],"attention":[12],"recent":[14],"years.":[15],"Existing":[16],"adversarial":[17,21,36,52,61,109,122,130,143,155],"RL":[18,33,47,110],"approaches":[19],"use":[20],"training":[22,37,53,87],"for":[23],"policy":[25,82],"improvement,":[26],"thus":[27,145],"enhancing":[28],"of":[32,43,89,129],"agents.":[34],"However,":[35],"severely":[38],"hinders":[39],"performance":[41,83,173],"improvement":[42],"agents":[44],"settings.":[48],"This":[49],"is":[50,54],"because":[51],"a":[55,75,106,147],"pessimistic":[56],"paradigm,":[58],"where":[59],"attack":[62,127],"patterns":[63],"aim":[64],"to":[65,79,96,151,163],"improve":[66,80,171],"agents\u2019":[68,172],"worst-case":[72],"scenarios.":[73],"Such":[74],"paradigm":[77],"struggles":[78],"unstable":[86],"process":[88],"RL,":[91],"thereby":[92],"making":[93],"it":[94],"challenging":[95],"enhance":[97],"ability.":[99,177],"To":[100],"tackle":[101],"this":[102],"problem,":[103],"we":[104],"propose":[105],"novel":[107],"approach,":[111,166],"namely":[112],"Soft":[113],"Adversarial":[114],"Offline":[115],"Reinforcement":[116],"Learning":[117],"(SAORL),":[118],"which":[119,167],"learns":[120],"soft":[121,154],"examples":[123,131],"by":[124],"reducing":[125],"strength":[128],"RL.":[134],"Specifically,":[135],"SAORL":[136,169],"proposes":[137],"Wasserstein-based":[139],"constraint":[140],"on":[141,161],"traditional":[142],"examples,":[144],"formulating":[146],"worse-case":[148],"optimization":[149],"problem":[150],"learn":[152],"examples.":[156],"We":[157],"conduct":[158],"extensive":[159],"experiments":[160],"D4RL":[162],"evaluate":[164],"our":[165],"demonstrates":[168],"can":[170],"and":[174],"zero-shot":[175]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}