{"id":"https://openalex.org/W4406890646","doi":"https://doi.org/10.1109/access.2025.3535679","title":"Safe Reinforcement Learning via Episodic Control","display_name":"Safe Reinforcement Learning via Episodic Control","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406890646","doi":"https://doi.org/10.1109/access.2025.3535679"},"language":"it","primary_location":{"id":"doi:10.1109/access.2025.3535679","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3535679","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3535679","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhuo Li","orcid":"https://orcid.org/0000-0002-0602-7664"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhuo Li","raw_affiliation_strings":["Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0602-7664","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103227499","display_name":"Derui Zhu","orcid":"https://orcid.org/0000-0002-9552-0097"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Derui Zhu","raw_affiliation_strings":["Chair of Cyber Trust, Technical University of Munich, Munich, Germany","Chair of Cyber Trust, Technical University of Munich, Garching, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9552-0097","affiliations":[{"raw_affiliation_string":"Chair of Cyber Trust, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Cyber Trust, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063714878","display_name":"Jens Gro\u00dfklags","orcid":"https://orcid.org/0000-0003-1093-1282"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Grossklags","raw_affiliation_strings":["Chair of Cyber Trust, Technical University of Munich, Munich, Germany","Chair of Cyber Trust, Technical University of Munich, Garching, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1093-1282","affiliations":[{"raw_affiliation_string":"Chair of Cyber Trust, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Cyber Trust, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.3042,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82666863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"35270","last_page":"35280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5130000114440918,"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":0.5130000114440918,"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/T10320","display_name":"Neural Networks and Applications","score":0.4510999917984009,"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":0.8061285018920898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.729049026966095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45294779539108276},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43830686807632446},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41191643476486206},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0968579351902008}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8061285018920898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729049026966095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45294779539108276},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43830686807632446},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41191643476486206},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0968579351902008},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3535679","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3535679","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:293b57a082904292aff63a05f6d21761","is_oa":true,"landing_page_url":"https://doaj.org/article/293b57a082904292aff63a05f6d21761","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 35270-35280 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3535679","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3535679","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1977655452","https://openalex.org/W2070570138","https://openalex.org/W2129462326","https://openalex.org/W2133354214","https://openalex.org/W2158782408","https://openalex.org/W2288565641","https://openalex.org/W2784709112","https://openalex.org/W2877093712","https://openalex.org/W2884165914","https://openalex.org/W2964082094","https://openalex.org/W2968940383","https://openalex.org/W2996037775","https://openalex.org/W2998069546","https://openalex.org/W3123348991","https://openalex.org/W3127561923","https://openalex.org/W3175558129","https://openalex.org/W3189480080","https://openalex.org/W3216656735","https://openalex.org/W4205678875","https://openalex.org/W4206497039","https://openalex.org/W4283794144","https://openalex.org/W4312299945","https://openalex.org/W4401042681","https://openalex.org/W4402402057","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6677145610","https://openalex.org/W6677959772","https://openalex.org/W6684037837","https://openalex.org/W6684921986","https://openalex.org/W6687063787","https://openalex.org/W6692846177","https://openalex.org/W6718359804","https://openalex.org/W6734330393","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6741002519","https://openalex.org/W6751725685","https://openalex.org/W6752155926","https://openalex.org/W6754857033","https://openalex.org/W6760822370","https://openalex.org/W6767486501","https://openalex.org/W6771280675","https://openalex.org/W6772744401","https://openalex.org/W6780559895","https://openalex.org/W6780587392","https://openalex.org/W6782701044","https://openalex.org/W6783117007","https://openalex.org/W6784630725","https://openalex.org/W6785187516","https://openalex.org/W6789855942","https://openalex.org/W6791277150","https://openalex.org/W6802704075","https://openalex.org/W6803314920","https://openalex.org/W6803709789","https://openalex.org/W6810667139","https://openalex.org/W6848768504","https://openalex.org/W6853251592","https://openalex.org/W6904861994","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Safe":[0,49,60,173],"reinforcement":[1],"learning":[2,11],"(Safe":[3],"RL)":[4],"aims":[5],"to":[6,54,74,84,201],"learn":[7],"policies":[8],"capable":[9],"of":[10,104,132,168,197],"and":[12,37,57,102,113,123,134,142,161,194,212],"adapting":[13],"within":[14],"complex":[15],"environments":[16],"while":[17,63],"ensuring":[18],"actions":[19],"remain":[20],"free":[21],"from":[22],"catastrophic":[23],"consequences.":[24],"This":[25,78,153],"is":[26],"a":[27,129],"critical":[28],"consideration":[29],"in":[30,88,110],"domains":[31],"such":[32],"as":[33,68],"robotics,":[34],"autonomous":[35],"vehicles,":[36],"healthcare.":[38],"Unlike":[39],"traditional":[40],"RL,":[41,93],"which":[42],"focuses":[43],"mainly":[44],"on":[45,96,128,171],"maximizing":[46],"episodic":[47,97,192],"rewards,":[48],"RL":[50,61,174],"integrates":[51],"safety":[52,198],"constraints":[53,199],"balance":[55,208],"rewards":[56,211],"safety.":[58,135,213],"Current":[59],"algorithms,":[62],"promising,":[64],"lack":[65],"sample":[66,86],"efficiency":[67,87],"they":[69],"require":[70],"extensive":[71],"environmental":[72],"interactions":[73],"perform":[75],"multi-objective":[76],"optimization.":[77,91,116],"paper":[79],"introduces":[80],"an":[81,206],"episodic-control-based":[82],"method":[83,119,170,187],"enhance":[85],"safe":[89,162],"policy":[90,115,147,158],"In":[92],"methods":[94],"based":[95,127],"control":[98,180],"involve":[99],"the":[100,146,157,166,202],"storing":[101,124],"replaying":[103],"past":[105],"experiences":[106],"or":[107],"episodes,":[108],"aiding":[109],"more":[111],"efficient":[112],"precise":[114],"Our":[117],"proposed":[118],"involves":[120],"clustering,":[121],"measuring,":[122],"previous":[125],"states":[126],"joint":[130],"metric":[131],"returns":[133,193],"Subsequently,":[136],"we":[137],"retrieve":[138],"these":[139],"state":[140],"measurements":[141],"incorporate":[143],"them":[144],"into":[145],"optimization":[148],"process":[149],"through":[150],"reward":[151],"shaping.":[152],"approach":[154],"effectively":[155],"guides":[156],"towards":[159],"high-return":[160],"decisions.":[163],"We":[164],"evaluate":[165],"performance":[167],"our":[169,186],"established":[172],"benchmarks,":[175],"including":[176],"six":[177],"safety-critical":[178],"agent":[179],"tasks.":[181],"The":[182],"results":[183],"demonstrate":[184],"that":[185],"can":[188],"concurrently":[189],"achieve":[190],"higher":[191],"fewer":[195],"violations":[196],"compared":[200],"baseline":[203],"methods,":[204],"suggesting":[205],"effective":[207],"between":[209],"earning":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}