{"id":"https://openalex.org/W4404688444","doi":"https://doi.org/10.1109/tnnls.2024.3496492","title":"GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model","display_name":"GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model","publication_year":2024,"publication_date":"2024-11-25","ids":{"openalex":"https://openalex.org/W4404688444","doi":"https://doi.org/10.1109/tnnls.2024.3496492","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030359"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3496492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3496492","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5026971084","display_name":"Zhehua Zhou","orcid":"https://orcid.org/0000-0001-9542-4858"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhehua Zhou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9542-4858","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuan Xie","orcid":"https://orcid.org/0000-0003-3981-8515"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xuan Xie","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3981-8515","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104291087","display_name":"Jiayang Song","orcid":"https://orcid.org/0009-0008-7093-9781"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiayang Song","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0009-0008-7093-9781","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhan Shu","orcid":"https://orcid.org/0000-0002-5933-254X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhan Shu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5933-254X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lei Ma","orcid":"https://orcid.org/0000-0002-8621-2420"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lei Ma","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8621-2420","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026971084"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.6623,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7629692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"36","issue":"6","first_page":"10678","last_page":"10692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9934999942779541,"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":0.9934999942779541,"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":0.9865000247955322,"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/T10524","display_name":"Traffic control and management","score":0.9732999801635742,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7312990427017212},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6686664819717407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.601241946220398},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.502079963684082},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.46074143052101135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4261285066604614},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42171624302864075},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41597461700439453},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4013172388076782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3400908410549164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16744336485862732},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.06517520546913147},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05673032999038696},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.046301305294036865}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7312990427017212},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6686664819717407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.601241946220398},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.502079963684082},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.46074143052101135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4261285066604614},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42171624302864075},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41597461700439453},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4013172388076782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3400908410549164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16744336485862732},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.06517520546913147},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05673032999038696},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.046301305294036865},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3496492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3496492","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40030359","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030359","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1716091338","display_name":null,"funder_award_id":"JPMJMI20B8","funder_id":"https://openalex.org/F4320338243","funder_display_name":"JST-Mirai Program"},{"id":"https://openalex.org/G3321578376","display_name":null,"funder_award_id":"RGPAS-2021-00034","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G4398550076","display_name":null,"funder_award_id":"DGECR-2021-00019","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G6681470965","display_name":null,"funder_award_id":"RGPIN-2021-02549","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320309207","display_name":"Grant Foundation","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320338243","display_name":"JST-Mirai Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1504265534","https://openalex.org/W1522399516","https://openalex.org/W1669104078","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W2006859604","https://openalex.org/W2070570138","https://openalex.org/W2073314543","https://openalex.org/W2128728535","https://openalex.org/W2140135625","https://openalex.org/W2143346970","https://openalex.org/W2152195021","https://openalex.org/W2187089797","https://openalex.org/W2342662072","https://openalex.org/W2543580944","https://openalex.org/W2736601468","https://openalex.org/W2784465508","https://openalex.org/W2804791273","https://openalex.org/W2889696653","https://openalex.org/W2948652605","https://openalex.org/W2949207039","https://openalex.org/W2963525569","https://openalex.org/W2968104655","https://openalex.org/W2968547875","https://openalex.org/W2977466517","https://openalex.org/W2979211489","https://openalex.org/W2981915592","https://openalex.org/W2994712737","https://openalex.org/W2998619042","https://openalex.org/W3033003934","https://openalex.org/W3034840734","https://openalex.org/W3036293943","https://openalex.org/W3091282566","https://openalex.org/W3092938557","https://openalex.org/W3093201391","https://openalex.org/W3094224934","https://openalex.org/W3122928565","https://openalex.org/W3127556163","https://openalex.org/W3127561923","https://openalex.org/W3153187775","https://openalex.org/W3168692131","https://openalex.org/W3176726917","https://openalex.org/W3187550742","https://openalex.org/W3195968524","https://openalex.org/W3207166640","https://openalex.org/W3211604259","https://openalex.org/W4206497039","https://openalex.org/W4211202104","https://openalex.org/W4214717370","https://openalex.org/W4220747123","https://openalex.org/W4221144242","https://openalex.org/W4221161274","https://openalex.org/W4226438853","https://openalex.org/W4246038204","https://openalex.org/W4255863451","https://openalex.org/W4281480521","https://openalex.org/W4283396661","https://openalex.org/W4285102169","https://openalex.org/W4292928781","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4296414154","https://openalex.org/W4297847176","https://openalex.org/W4300672471","https://openalex.org/W4306705058","https://openalex.org/W4307230233","https://openalex.org/W4319165238","https://openalex.org/W4378805020","https://openalex.org/W4385767976","https://openalex.org/W4387838703","https://openalex.org/W4388184601","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6680657880","https://openalex.org/W6683517036","https://openalex.org/W6704571135","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6741002519","https://openalex.org/W6747790125","https://openalex.org/W6751535212","https://openalex.org/W6751725685","https://openalex.org/W6754113743","https://openalex.org/W6767486501","https://openalex.org/W6768617876","https://openalex.org/W6771280675","https://openalex.org/W6779812412","https://openalex.org/W6782604916","https://openalex.org/W6785187516","https://openalex.org/W6790964287","https://openalex.org/W6796690604","https://openalex.org/W6803413346","https://openalex.org/W6803800456","https://openalex.org/W6809864479","https://openalex.org/W6838701874","https://openalex.org/W6842458895","https://openalex.org/W6843754643","https://openalex.org/W6846122673","https://openalex.org/W6858013149","https://openalex.org/W6858029487"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"Safe":[0],"reinforcement":[1,13],"learning":[2,9,14,42,162],"(SRL)":[3],"aims":[4],"to":[5,37,45,89,121,154,178,195],"realize":[6],"a":[7,57,91,99,175,196],"safe":[8],"process":[10,96],"for":[11,136],"deep":[12],"(DRL)":[15],"algorithms":[16],"by":[17,108],"incorporating":[18],"safety":[19,60,105,134,156],"constraints.":[20,106],"However,":[21],"the":[22,40,66,73,103,110,116,119,123,160],"efficacy":[23],"of":[24,68,75,102,118,125,199],"SRL":[25,76,137,144,181,190,202],"approaches":[26,145],"often":[27],"relies":[28],"on":[29,142],"accurate":[30],"function":[31],"approximations,":[32],"which":[33],"are":[34],"notably":[35],"challenging":[36],"achieve":[38],"in":[39,54,159],"early":[41,161],"stages":[43],"due":[44],"data":[46,69],"insufficiency.":[47],"To":[48],"address":[49],"this":[50,55],"issue,":[51],"we":[52,83],"introduce,":[53],"work,":[56],"novel":[58,176],"generalizable":[59],"enhancer":[61],"(GenSafe)":[62],"that":[63],"can":[64],"overcome":[65],"challenge":[67],"insufficiency":[70],"and":[71,146,201],"enhance":[72],"performance":[74],"approaches.":[77],"Leveraging":[78],"model":[79],"order":[80,93],"reduction":[81],"techniques,":[82],"first":[84],"propose":[85],"an":[86,132],"innovative":[87],"method":[88],"construct":[90],"reduced":[92],"Markov":[94],"decision":[95],"(ROMDP)":[97],"as":[98,131],"low-dimensional":[100],"approximator":[101],"original":[104],"Then,":[107],"solving":[109],"reformulated":[111],"ROMDP-based":[112],"constraints,":[113],"GenSafe":[114,129,141,171],"refines":[115],"actions":[117],"agent":[120],"increase":[122],"possibility":[124],"constraint":[126],"satisfaction.":[127],"Essentially,":[128],"acts":[130],"additional":[133],"layer":[135],"algorithms.":[138],"We":[139],"evaluate":[140],"multiple":[143],"benchmark":[147],"problems.":[148,203],"The":[149],"results":[150],"demonstrate":[151],"its":[152],"capability":[153],"improve":[155],"performance,":[157],"especially":[158],"phases,":[163],"while":[164],"maintaining":[165],"satisfactory":[166],"task":[167],"performance.":[168],"Our":[169],"proposed":[170],"not":[172],"only":[173],"offers":[174],"measure":[177],"augment":[179],"existing":[180],"methods":[182],"but":[183],"also":[184],"shows":[185],"broad":[186],"compatibility":[187],"with":[188],"various":[189],"algorithms,":[191],"making":[192],"it":[193],"applicable":[194],"wide":[197],"range":[198],"systems":[200]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}