{"id":"https://openalex.org/W4388887084","doi":"https://doi.org/10.1145/3605764.3623913","title":"Task-Agnostic Safety for Reinforcement Learning","display_name":"Task-Agnostic Safety for Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-21","ids":{"openalex":"https://openalex.org/W4388887084","doi":"https://doi.org/10.1145/3605764.3623913"},"language":"en","primary_location":{"id":"doi:10.1145/3605764.3623913","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605764.3623913","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605764.3623913","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3605764.3623913","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017750516","display_name":"Md Asifur Rahman","orcid":"https://orcid.org/0000-0001-9020-2789"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Asifur Rahman","raw_affiliation_strings":["Wake Forest University, Winston-Salem, NC, USA"],"raw_orcid":"https://orcid.org/0000-0001-9020-2789","affiliations":[{"raw_affiliation_string":"Wake Forest University, Winston-Salem, NC, USA","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057127359","display_name":"Sarra Alqahtani","orcid":"https://orcid.org/0000-0003-4572-7150"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarra Alqahtani","raw_affiliation_strings":["Wake Forest University, Winston-Salem, NC, USA"],"raw_orcid":"https://orcid.org/0000-0003-4572-7150","affiliations":[{"raw_affiliation_string":"Wake Forest University, Winston-Salem, NC, USA","institution_ids":["https://openalex.org/I47251452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017750516"],"corresponding_institution_ids":["https://openalex.org/I47251452"],"apc_list":null,"apc_paid":null,"fwci":0.3408,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67054645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"139","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944999814033508,"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":0.9944999814033508,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9894999861717224,"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":0.9271746873855591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751774787902832},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.669086754322052},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6026111841201782},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5885868668556213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4982123374938965},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4320315718650818},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.35946935415267944},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.353823184967041},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.119060218334198},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09351330995559692}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9271746873855591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751774787902832},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.669086754322052},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6026111841201782},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5885868668556213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4982123374938965},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4320315718650818},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.35946935415267944},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.353823184967041},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.119060218334198},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09351330995559692},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605764.3623913","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605764.3623913","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605764.3623913","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3605764.3623913","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605764.3623913","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605764.3623913","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4711214724","display_name":null,"funder_award_id":"2105007","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G542504877","display_name":null,"funder_award_id":"2105007","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388887084.pdf","grobid_xml":"https://content.openalex.org/works/W4388887084.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W7221745","https://openalex.org/W1506085041","https://openalex.org/W2101075098","https://openalex.org/W2942465044","https://openalex.org/W2963575966","https://openalex.org/W2964040381","https://openalex.org/W2968547875","https://openalex.org/W2998401161","https://openalex.org/W3009331570","https://openalex.org/W3150718622","https://openalex.org/W3182474098","https://openalex.org/W3186708588","https://openalex.org/W4214646922","https://openalex.org/W4233840023","https://openalex.org/W4312254929"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Reinforcement":[0,82],"learning":[1,19,92],"(RL)":[2],"has":[3],"been":[4],"an":[5,64],"attractive":[6],"potential":[7],"for":[8,28,81,125],"designing":[9],"autonomous":[10],"systems":[11],"due":[12],"to":[13,51,67,86],"its":[14],"learning-by-exploration":[15],"approach.":[16],"However,":[17],"this":[18,38,75],"process":[20],"makes":[21],"RL":[22,90,114,144],"inherently":[23],"vulnerable":[24],"and":[25,46,71,98,108,141,160],"thus":[26],"unsuitable":[27],"applications":[29],"where":[30,139],"safety":[31,47,88,178],"is":[32,106],"a":[33,57,69,93,122,136],"top":[34],"priority.":[35],"To":[36,74,128],"address":[37],"issue,":[39],"researchers":[40],"have":[41],"either":[42],"jointly":[43],"optimized":[44],"task":[45,115],"or":[48],"imposed":[49],"constraints":[50],"restrict":[52],"exploration.":[53],"This":[54],"paper":[55],"takes":[56],"different":[58],"approach,":[59],"by":[60,91,174],"utilizing":[61],"exploration":[62],"as":[63],"adaptive":[65],"means":[66],"learn":[68],"robust":[70],"safe":[72,143],"behavior.":[73],"end,":[76],"we":[77,134],"propose":[78],"Task-Agnostic":[79],"Safety":[80],"Learning":[83],"(TAS-RL)":[84],"framework":[85],"ensure":[87],"in":[89,117,148,162,181,190],"representation":[94],"of":[95,132],"unsafe":[96],"behaviors":[97],"excluding":[99],"them":[100],"from":[101],"the":[102,118,126,130,163,191],"agent's":[103],"policy.":[104],"TAS-RL":[105,140,170],"task-agnostic":[107],"can":[109],"be":[110],"integrated":[111],"with":[112,185],"any":[113],"policy":[116],"same":[119],"environment,":[120],"providing":[121],"self-protection":[123],"layer":[124],"system.":[127],"evaluate":[129],"robustness":[131],"TAS-RL,":[133],"present":[135],"novel":[137],"study":[138],"7":[142],"baselines":[145,173],"are":[146],"tested":[147],"constrained":[149],"Markov":[150],"decision":[151],"processes":[152],"(CMDP)":[153],"environments":[154],"under":[155],"white-box":[156],"action":[157,183],"space":[158,184],"perturbations":[159],"changes":[161],"environment":[164,193],"dynamics.":[165,194],"The":[166],"results":[167],"show":[168],"that":[169],"outperforms":[171],"all":[172],"achieving":[175],"consistent":[176],"near-zero":[177],"constraint":[179],"violations":[180],"continuous":[182],"10":[186],"times":[187],"more":[188],"variations":[189],"testing":[192]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}