{"id":"https://openalex.org/W4368408202","doi":"https://doi.org/10.1145/3576841.3585936","title":"Self-Preserving Genetic Algorithms for Safe Learning in Discrete Action Spaces","display_name":"Self-Preserving Genetic Algorithms for Safe Learning in Discrete Action Spaces","publication_year":2023,"publication_date":"2023-05-04","ids":{"openalex":"https://openalex.org/W4368408202","doi":"https://doi.org/10.1145/3576841.3585936"},"language":"en","primary_location":{"id":"doi:10.1145/3576841.3585936","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3576841.3585936","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3576841.3585936","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3576841.3585936","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028566361","display_name":"Preston K. Robinette","orcid":"https://orcid.org/0000-0002-4906-2179"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Preston K. Robinette","raw_affiliation_strings":["Vanderbilt University, Nashville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-4906-2179","affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062691664","display_name":"Nathaniel Hamilton","orcid":"https://orcid.org/0000-0002-7147-1964"},"institutions":[{"id":"https://openalex.org/I4210087855","display_name":"Parallax Research (United States)","ror":"https://ror.org/006ejj273","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087855"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel P. Hamilton","raw_affiliation_strings":["Parallax Advanced Research, Beavercreek, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-7147-1964","affiliations":[{"raw_affiliation_string":"Parallax Advanced Research, Beavercreek, OH, USA","institution_ids":["https://openalex.org/I4210087855"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067901159","display_name":"Taylor T. Johnson","orcid":"https://orcid.org/0000-0001-8021-9923"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor T. Johnson","raw_affiliation_strings":["Vanderbilt University, Nashville, TN, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8021-9923","affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN, United States of America","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028566361"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":0.1704,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53111598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"110","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9930999875068665,"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":0.9930999875068665,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12810","display_name":"Real-time simulation and control systems","score":0.9857000112533569,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7578457593917847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5929679274559021},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5044254064559937},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.4741879403591156},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4669573903083801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46501997113227844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4578193426132202},{"id":"https://openalex.org/keywords/safety-assurance","display_name":"Safety assurance","score":0.4515770971775055},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3049370050430298},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17883190512657166}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7578457593917847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5929679274559021},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5044254064559937},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.4741879403591156},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4669573903083801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46501997113227844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4578193426132202},{"id":"https://openalex.org/C112805685","wikidata":"https://www.wikidata.org/wiki/Q10566551","display_name":"Safety assurance","level":2,"score":0.4515770971775055},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3049370050430298},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17883190512657166},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3576841.3585936","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3576841.3585936","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3576841.3585936","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3576841.3585936","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3576841.3585936","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3576841.3585936","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G114342927","display_name":null,"funder_award_id":"FA9550-21-F-0003","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1320817743","display_name":null,"funder_award_id":"FA9550-21-F-0003","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G1934839346","display_name":null,"funder_award_id":"FA9550-23-1-0135","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G2194724504","display_name":null,"funder_award_id":"FA9550-21-F-0003","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3622468541","display_name":null,"funder_award_id":"FA9550-21-F-0003","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G5784413458","display_name":null,"funder_award_id":"FA9550-22-1-0019","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6228126205","display_name":null,"funder_award_id":"FA9550-21-F-0003","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"},{"id":"https://openalex.org/G7999210852","display_name":null,"funder_award_id":"FA9550-21-F-0003","funder_id":"https://openalex.org/F4320333566","funder_display_name":"National Defense Science and Engineering Graduate"},{"id":"https://openalex.org/G8005326599","display_name":null,"funder_award_id":"2028001","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8289759875","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333566","display_name":"National Defense Science and Engineering Graduate","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4368408202.pdf","grobid_xml":"https://content.openalex.org/works/W4368408202.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1582099797","https://openalex.org/W1977655452","https://openalex.org/W1988543053","https://openalex.org/W2091565802","https://openalex.org/W2153353727","https://openalex.org/W2591980212","https://openalex.org/W2788125442","https://openalex.org/W2884730950","https://openalex.org/W2898035736","https://openalex.org/W2962853428","https://openalex.org/W2963575966","https://openalex.org/W2982316857","https://openalex.org/W3003931103","https://openalex.org/W3028345072","https://openalex.org/W3094236223","https://openalex.org/W3102804344","https://openalex.org/W3103752844","https://openalex.org/W3121342653","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W4391331176"],"abstract_inverted_index":{"Self-Preserving":[0],"Genetic":[1],"Algorithms":[2],"(SPGA)":[3],"combine":[4],"the":[5,34,40,56,59,65,122,133,153,267],"evolutionary":[6,123],"strategy":[7,124],"of":[8,25,39,58,67,69,83,125,152,159,182,244,269],"a":[9,23,90,126,141],"genetic":[10,127],"algorithm":[11],"with":[12,132,137,165,208,257],"safety":[13,32,57,134,173,199,254],"assurance":[14,172],"methods":[15],"commonly":[16],"implemented":[17],"in":[18,33,48,64,71],"safe":[19,94,142,177,245,271],"reinforcement":[20,26],"learning":[21,27,43,143,272],"(SRL),":[22],"branch":[24],"(RL)":[28],"that":[29,100,117,145],"accounts":[30],"for":[31,55,179],"exploration":[35],"and":[36,114,169,194,196,202,218,227,242,253],"decision-making":[37],"process":[38],"agent.":[41],"Safe":[42],"approaches":[44],"are":[45,97,206,221],"especially":[46],"important":[47],"safety-critical":[49],"environments,":[50],"where":[51],"failure":[52],"to":[53,76,93,148,175,188,214,232,237],"account":[54],"controlled":[60],"system":[61],"could":[62],"result":[63],"loss":[66],"millions":[68],"dollars":[70],"hardware":[72],"or":[73],"bodily":[74],"harm":[75],"people":[77],"working":[78],"nearby,":[79],"as":[80,110],"is":[81,89,118,146],"true":[82],"many":[84,98],"cyber-physical":[85],"systems.":[86],"While":[87],"SRL":[88,211,219],"viable":[91],"approach":[92],"learning,":[95],"there":[96],"challenges":[99],"must":[101],"be":[102],"taken":[103],"into":[104],"consideration":[105],"when":[106],"training":[107,260],"agents,":[108],"such":[109],"sample":[111],"efficiency,":[112],"stability,":[113],"exploration---an":[115],"issue":[116],"easily":[119],"addressed":[120],"by":[121],"algorithm.":[128],"By":[129],"combining":[130],"GAs":[131],"mechanisms":[135],"used":[136],"SRL,":[138],"SPGA":[139,164,217,249],"offers":[140],"alternative":[144],"able":[147],"explore":[149],"large":[150],"areas":[151],"solution":[154],"space,":[155],"addressing":[156],"SRL's":[157],"challenge":[158],"exploration.":[160],"This":[161],"work":[162],"implements":[163],"both":[166],"action":[167,184,246],"masking":[168],"run":[170],"time":[171,236],"strategies":[174],"evolve":[176],"controllers":[178,213,220],"three":[180],"types":[181],"discrete":[183],"space":[185],"environments":[186],"applicable":[187],"cyber":[189],"physical":[190],"systems":[191],"(control,":[192],"routing,":[193],"operations)":[195],"under":[197],"various":[198],"conditions.":[200],"Training":[201],"testing":[203],"evaluation":[204,247],"metrics":[205],"compared":[207],"results":[209,256],"from":[210],"trained":[212,222],"validate":[215],"results.":[216],"across":[223],"5":[224],"random":[225],"seeds":[226],"evaluated":[228],"on":[229,264],"500":[230],"episodes":[231],"calculate":[233],"average":[234,239],"wall":[235],"train,":[238],"expected":[240],"return,":[241],"percentage":[243],"metrics.":[248],"achieves":[250],"comparable":[251],"reward":[252],"performance":[255],"significantly":[258],"improved":[259],"efficiency":[261],"(55x":[262],"faster":[263],"average),":[265],"demonstrating":[266],"effectiveness":[268],"this":[270],"approach.":[273]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}