{"id":"https://openalex.org/W4411399924","doi":"https://doi.org/10.1007/s10994-025-06810-4","title":"All-time safety and sample-efficient meta update for online safe meta reinforcement learning under Markov task transition","display_name":"All-time safety and sample-efficient meta update for online safe meta reinforcement learning under Markov task transition","publication_year":2025,"publication_date":"2025-06-18","ids":{"openalex":"https://openalex.org/W4411399924","doi":"https://doi.org/10.1007/s10994-025-06810-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-025-06810-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06810-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06810-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06810-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045036436","display_name":"Zhenyuan Yuan","orcid":"https://orcid.org/0000-0001-6195-1481"},"institutions":[{"id":"https://openalex.org/I4387930269","display_name":"Virginia Tech Transportation Institute","ror":"https://ror.org/05953j253","country_code":null,"type":"facility","lineage":["https://openalex.org/I4387930269","https://openalex.org/I859038795"]},{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhenyuan Yuan","raw_affiliation_strings":["Virginia Tech Transportation Institute, Virginia Tech, Blacksburg, VA, 24060, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech Transportation Institute, Virginia Tech, Blacksburg, VA, 24060, USA","institution_ids":["https://openalex.org/I859038795","https://openalex.org/I4387930269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101828020","display_name":"Siyuan Xu","orcid":"https://orcid.org/0000-0002-7999-9712"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyuan Xu","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, 16802, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101766328","display_name":"Minghui Zhu","orcid":"https://orcid.org/0000-0003-3879-7820"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minghui Zhu","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, 16802, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045036436"],"corresponding_institution_ids":["https://openalex.org/I4387930269","https://openalex.org/I859038795"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06630508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"114","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9850000143051147,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8643785119056702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6721330881118774},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6275779008865356},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6050640940666199},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.561388373374939},{"id":"https://openalex.org/keywords/metamodeling","display_name":"Metamodeling","score":0.5340121388435364},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5075770616531372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48407045006752014},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.47348105907440186},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.44775599241256714},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.443021684885025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4335469603538513},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.19138506054878235},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1498461663722992},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14007630944252014},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12145474553108215},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07641178369522095}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8643785119056702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6721330881118774},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6275779008865356},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6050640940666199},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.561388373374939},{"id":"https://openalex.org/C86610423","wikidata":"https://www.wikidata.org/wiki/Q1925081","display_name":"Metamodeling","level":2,"score":0.5340121388435364},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5075770616531372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48407045006752014},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.47348105907440186},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.44775599241256714},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.443021684885025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4335469603538513},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.19138506054878235},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1498461663722992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14007630944252014},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12145474553108215},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07641178369522095},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-025-06810-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06810-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06810-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-025-06810-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06810-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06810-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2296916099","display_name":null,"funder_award_id":"ECCS-1","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2955067590","display_name":null,"funder_award_id":"1710859","funder_id":"https://openalex.org/F4320337392","funder_display_name":"Division of Electrical, Communications and Cyber Systems"},{"id":"https://openalex.org/G3826748516","display_name":null,"funder_award_id":"ECCS-1710859","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4017200989","display_name":"NRI: INT: COLLAB: Interactive and collaborative robot-assisted emergency evacuations","funder_award_id":"1830390","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4562456859","display_name":"CAREER: New control-theoretic approaches for cyber-physical privacy","funder_award_id":"1846706","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5918884595","display_name":null,"funder_award_id":"CNS-1830390","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7011942308","display_name":"Data-driven distributed control of mobile robotic networks: Where machine learning meets game theory","funder_award_id":"1710859","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7258483247","display_name":null,"funder_award_id":"ECCS-1846706","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7783715049","display_name":null,"funder_award_id":"ECCS-1710859","funder_id":"https://openalex.org/F4320337392","funder_display_name":"Division of Electrical, Communications and Cyber Systems"},{"id":"https://openalex.org/G7805592574","display_name":null,"funder_award_id":"1846706","funder_id":"https://openalex.org/F4320337392","funder_display_name":"Division of Electrical, Communications and Cyber Systems"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F2651700613","display_name":"Penn State College of Engineering, Pennsylvania State University","ror":null},{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320310419","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411399924.pdf","grobid_xml":"https://content.openalex.org/works/W4411399924.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W1424654272","https://openalex.org/W1536997931","https://openalex.org/W1585575029","https://openalex.org/W1840625103","https://openalex.org/W1845972764","https://openalex.org/W1879112630","https://openalex.org/W1964262340","https://openalex.org/W1965878388","https://openalex.org/W1970041563","https://openalex.org/W1979289676","https://openalex.org/W1983497631","https://openalex.org/W1986998777","https://openalex.org/W1990437501","https://openalex.org/W2013406658","https://openalex.org/W2052029349","https://openalex.org/W2101075098","https://openalex.org/W2108888882","https://openalex.org/W2121110499","https://openalex.org/W2134491302","https://openalex.org/W2149882723","https://openalex.org/W2160908800","https://openalex.org/W2162849300","https://openalex.org/W2165216595","https://openalex.org/W2169401877","https://openalex.org/W2169619645","https://openalex.org/W2173248099","https://openalex.org/W2260756217","https://openalex.org/W2518885560","https://openalex.org/W2604763608","https://openalex.org/W2618318883","https://openalex.org/W2752041096","https://openalex.org/W2781726626","https://openalex.org/W2923504512","https://openalex.org/W2925446857","https://openalex.org/W2937697512","https://openalex.org/W2963525569","https://openalex.org/W2990138404","https://openalex.org/W3033003934","https://openalex.org/W3038180127","https://openalex.org/W3089932849","https://openalex.org/W3093358689","https://openalex.org/W3120459386","https://openalex.org/W3135301907","https://openalex.org/W3164515101","https://openalex.org/W3168269639","https://openalex.org/W3168575058","https://openalex.org/W3178748050","https://openalex.org/W3190791531","https://openalex.org/W3212871871","https://openalex.org/W3217314940","https://openalex.org/W4205841652","https://openalex.org/W4206497039","https://openalex.org/W4226026450","https://openalex.org/W4314947433","https://openalex.org/W4315488635","https://openalex.org/W4315606134","https://openalex.org/W4321161785","https://openalex.org/W4324116431","https://openalex.org/W4379256329","https://openalex.org/W4387430858","https://openalex.org/W4399115808","https://openalex.org/W4403570070","https://openalex.org/W6638018090","https://openalex.org/W6682367392","https://openalex.org/W6730267373","https://openalex.org/W6737893269","https://openalex.org/W6760842081","https://openalex.org/W6796403369","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2156021013","https://openalex.org/W2016648086","https://openalex.org/W3105579180","https://openalex.org/W4281791088","https://openalex.org/W4297823484"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"studies":[3],"the":[4,59,69,84,90,101,104,107,111,115,151],"issues":[5],"of":[6,38,71,86,89,153],"ensuring":[7],"all-time":[8,65],"safety":[9,66],"and":[10,43,63,106,117,137,142,150,155],"sample-efficient":[11,45],"meta":[12,17,47,91,108],"update":[13,48,88],"in":[14],"online":[15,46,87],"safe":[16],"reinforcement":[18,124],"learning":[19,125],"(MRL)":[20],"on":[21,131],"physical":[22],"agents":[23],"(e.g.,":[24],"mobile":[25],"robots).":[26],"We":[27,127],"propose":[28],"a":[29,39,44,55,76,96],"novel":[30],"masked":[31],"Follow-the-Last-Parameter-Policy":[32],"(FTLPP)":[33],"framework,":[34],"which":[35],"is":[36,93,119],"composed":[37],"policy":[40,51,62,97],"masking":[41,52,56],"framework":[42,53],"method.":[49],"The":[50],"applies":[54],"function":[57],"over":[58],"learned":[60],"control":[61],"ensures":[64],"by":[67],"suppressing":[68],"probability":[70],"executing":[72],"unsafe":[73],"actions":[74],"to":[75],"sufficiently":[77],"small":[78],"value.":[79],"To":[80],"enhance":[81],"sample":[82],"efficiency,":[83],"problem":[85],"parameter":[92],"transformed":[94],"into":[95],"optimization":[98],"problem,":[99],"where":[100],"tasks":[102],"are":[103,114],"states":[105],"parameters":[109],"for":[110],"next":[112],"task":[113],"actions,":[116],"then":[118],"solved":[120],"using":[121],"an":[122],"off-policy":[123],"algorithm.":[126],"evaluate":[128],"our":[129],"method":[130],"Frozen":[132],"Lake,":[133],"Acrobot,":[134],"Half":[135],"Cheetah":[136],"Hopper":[138],"from":[139],"OpenAI":[140],"gym":[141],"compare":[143],"it":[144],"with":[145],"baseline":[146],"methods":[147],"Meta":[148],"SRL":[149],"variants":[152],"FTML":[154],"SAILR.":[156]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}