{"id":"https://openalex.org/W4386815328","doi":"https://doi.org/10.14428/esann/2023.es2023-97","title":"DEFENDER: DTW-Based Episode Filtering Using Demonstrations for Enhancing RL Safety","display_name":"DEFENDER: DTW-Based Episode Filtering Using Demonstrations for Enhancing RL Safety","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386815328","doi":"https://doi.org/10.14428/esann/2023.es2023-97"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2023.es2023-97","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-97","pdf_url":"http://dx.doi.org/10.14428/esann/2023.es2023-97","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.14428/esann/2023.es2023-97","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029312365","display_name":"Andr\u00e9 Correia","orcid":"https://orcid.org/0000-0002-0119-9790"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Correia","raw_affiliation_strings":["Universidade da Beira Interior and NOVA LINCS Covilh - Portugal","Universidade da Beira Interior and NOVA LINCS Covilh -Portugal","Universidade da Beira Interior and NOVA LINCS Covilh\u00e3 -Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade da Beira Interior and NOVA LINCS Covilh - Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Universidade da Beira Interior and NOVA LINCS Covilh -Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Universidade da Beira Interior and NOVA LINCS Covilh\u00e3 -Portugal","institution_ids":["https://openalex.org/I161321875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009791474","display_name":"Lu\u0131\u0301s A. Alexandre","orcid":"https://orcid.org/0000-0002-5133-5025"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Lu\u00eds Alexandre","raw_affiliation_strings":["Universidade da Beira Interior and NOVA LINCS Covilh - Portugal","Universidade da Beira Interior and NOVA LINCS Covilh -Portugal","Universidade da Beira Interior and NOVA LINCS Covilh\u00e3 -Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade da Beira Interior and NOVA LINCS Covilh - Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Universidade da Beira Interior and NOVA LINCS Covilh -Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Universidade da Beira Interior and NOVA LINCS Covilh\u00e3 -Portugal","institution_ids":["https://openalex.org/I161321875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11545931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"303","last_page":"308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9858999848365784,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8288564682006836},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8168694972991943},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.73160719871521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7206499576568604},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6928532719612122},{"id":"https://openalex.org/keywords/crash","display_name":"Crash","score":0.5741702318191528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5296860933303833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4644626975059509},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4308794140815735},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19222670793533325},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11801251769065857}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8288564682006836},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8168694972991943},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.73160719871521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7206499576568604},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6928532719612122},{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.5741702318191528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5296860933303833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4644626975059509},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4308794140815735},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19222670793533325},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11801251769065857},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2023.es2023-97","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-97","pdf_url":"http://dx.doi.org/10.14428/esann/2023.es2023-97","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2023.es2023-97","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2023.es2023-97","pdf_url":"http://dx.doi.org/10.14428/esann/2023.es2023-97","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6348741101","display_name":null,"funder_award_id":"UIDB/04516/2020","funder_id":"https://openalex.org/F4320331406","funder_display_name":"NOVA Laboratory for Computer Science and Informatics"},{"id":"https://openalex.org/G8725369612","display_name":"NOVA Laboratory for Computer Science and Informatics","funder_award_id":"UIDB/04516/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320331406","display_name":"NOVA Laboratory for Computer Science and Informatics","ror":null},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386815328.pdf","grobid_xml":"https://content.openalex.org/works/W4386815328.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1931877416","https://openalex.org/W2144994235","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2924156739","https://openalex.org/W2966735560","https://openalex.org/W4237171445","https://openalex.org/W4283319080","https://openalex.org/W4286229688","https://openalex.org/W4313010279"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2026516036","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W626940945","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Deploying":[0],"reinforcement":[1],"learning":[2,17],"agents":[3,41],"in":[4,136],"the":[5,13,37,46,50,62,67,79,82,126,130,141,144],"real":[6],"world":[7],"can":[8,97],"be":[9,98],"challenging":[10],"due":[11],"to":[12,35,100],"risks":[14],"associated":[15],"with":[16,52,91],"through":[18],"trial":[19],"and":[20,32,60,77,96,114,135],"error.We":[21],"propose":[22],"a":[23],"task-agnostic":[24],"method":[25,44,88,105,123],"that":[26,121],"leverages":[27],"small":[28],"sets":[29,54],"of":[30,39,49,55,81,84,129,143],"safe":[31],"unsafe":[33,68],"demonstrations":[34,56,85],"improve":[36],"safety":[38],"RL":[40,94,117],"during":[42],"learning.The":[43],"compares":[45],"current":[47],"trajectory":[48,63],"agent":[51,131],"both":[53],"at":[57],"every":[58],"step,":[59],"filters":[61],"if":[64],"it":[65],"resembles":[66],"demonstrations.We":[69],"perform":[70],"ablation":[71],"studies":[72],"on":[73,86,106],"different":[74],"filtering":[75],"strategies":[76],"investigate":[78],"impact":[80],"number":[83],"performance.Our":[87],"is":[89],"compatible":[90],"any":[92,101],"stand-alone":[93,145],"algorithm":[95],"applied":[99],"task.We":[102],"evaluate":[103],"our":[104,122],"three":[107],"tasks":[108],"from":[109],"OpenAI":[110],"Gym's":[111],"Mujoco":[112],"benchmark":[113],"two":[115],"state-of-the-art":[116],"algorithms.The":[118],"results":[119],"demonstrate":[120],"significantly":[124],"reduces":[125],"crash":[127],"rate":[128],"while":[132],"converging":[133],"to,":[134],"most":[137],"cases":[138],"even":[139],"improving,":[140],"performance":[142],"agent.":[146]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}