{"id":"https://openalex.org/W3159612713","doi":"https://doi.org/10.1109/ciss50987.2021.9400210","title":"Model-free safe policy learning via hard action barrier functions","display_name":"Model-free safe policy learning via hard action barrier functions","publication_year":2021,"publication_date":"2021-03-24","ids":{"openalex":"https://openalex.org/W3159612713","doi":"https://doi.org/10.1109/ciss50987.2021.9400210","mag":"3159612713"},"language":"en","primary_location":{"id":"doi:10.1109/ciss50987.2021.9400210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss50987.2021.9400210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","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/A5018563588","display_name":"Agustin Castellano","orcid":"https://orcid.org/0000-0003-3491-5746"},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica de Uruguay","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Agustin Castellano","raw_affiliation_strings":["Universidad de la Republica, Montevideo, Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de la Republica, Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029019906","display_name":"Juan Andr\u00e9s Bazerque","orcid":"https://orcid.org/0000-0001-9950-1208"},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica de Uruguay","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Juan Bazerque","raw_affiliation_strings":["Universidad de la Republica, Montevideo, Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de la Republica, Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032910355","display_name":"Enrique Mallada","orcid":"https://orcid.org/0000-0003-1568-1833"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enrique Mallada","raw_affiliation_strings":["Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05602979,"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":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8485999703407288,"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":0.8485999703407288,"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/T11357","display_name":"Risk and Safety Analysis","score":0.8360000252723694,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7590000033378601,"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/computer-science","display_name":"Computer science","score":0.6215897798538208},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5715510845184326},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07761049270629883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6215897798538208},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5715510845184326},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07761049270629883},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ciss50987.2021.9400210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss50987.2021.9400210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3495421339","display_name":null,"funder_award_id":"TRIPODS 1934979,CNS 1544771,EPCN 1711188,AMPS 1736448,CAREER 1752362","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"To":[0],"enable":[1],"model-free":[2],"learning":[3,151],"of":[4,16,34,60,121,150],"safe":[5],"policies":[6],"in":[7,83,176,181,196],"Constrained":[8],"Markov":[9],"Decision":[10],"Processes,":[11],"we":[12,56,94,109],"advance":[13],"the":[14,35,38,58,116,122,147,159,166,177,187,206],"notion":[15,59],"penalties":[17,67],"as":[18,68,140],"an":[19,111],"information":[20],"source":[21],"that":[22,79,99,114,170,184,201],"complements":[23],"rewards":[24],"and":[25,72,142],"is":[26],"similarly":[27],"acquired":[28],"from":[29,102,152],"experience.":[30],"Without":[31],"prior":[32],"knowledge":[33],"safety":[36,101],"constraints,":[37],"agent":[39],"must":[40,80,202],"resort":[41],"to":[42,47,52,85,172,208],"penalties-that":[43],"signal":[44],"infeasibility-in":[45],"order":[46,84],"learn":[48],"which":[49,65],"actions":[50],"lead":[51],"constraint":[53,174],"violations.":[54],"Accordingly,":[55],"define":[57],"hard":[61],"action":[62,117,169],"barrier":[63,118],"functions,":[64],"incorporate":[66],"(0,+infinity)":[69],"binary":[70],"information,":[71],"gradually":[73],"reveal":[74],"implicit":[75],"state-action":[76],"pair":[77],"constraints":[78,188],"be":[81,203],"satisfied":[82],"avoid":[86],"(possibly":[87],"future)":[88],"unsafe":[89,168],"states.":[90],"Using":[91],"this":[92,107],"notion,":[93],"characterize":[95],"a":[96,127,173,182,197,209],"separation":[97],"principle":[98,108],"decouples":[100],"reward":[103,124],"maximization.":[104],"Based":[105],"on":[106,205],"propose":[110],"adaptive":[112],"algorithm":[113,131],"learns":[115],"function":[119],"independently":[120],"specific":[123],"structure.":[125],"As":[126],"result,":[128],"our":[129],"Barrier-Learning":[130],"can":[132],"wrap":[133],"around":[134],"standard":[135],"on-and":[136],"off-policy":[137],"algorithms":[138,195],"such":[139],"Q-Learning":[141],"SARSA.":[143],"Our":[144],"solution":[145],"has":[146],"added":[148],"benefit":[149],"previous":[153],"mistakes":[154],"by":[155],"avoiding":[156],"bumping":[157],"into":[158],"same":[160,167],"rock":[161],"twice,":[162],"i.e.,":[163],"not":[164],"taking":[165],"led":[171],"violation":[175],"past.":[178],"This":[179],"results":[180],"policy":[183],"complies":[185],"with":[186,199],"almost":[189],"surely.":[190],"We":[191],"demonstrate":[192],"these":[193],"combined":[194],"grid-walk":[198],"walls":[200],"avoided":[204],"way":[207],"target.":[210]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}