{"id":"https://openalex.org/W4368362731","doi":"https://doi.org/10.1145/3576841.3589635","title":"DEMO: Self-Preserving Genetic Algorithms vs. Safe Reinforcement Learning in Discrete Action Spaces","display_name":"DEMO: Self-Preserving Genetic Algorithms vs. Safe Reinforcement Learning in Discrete Action Spaces","publication_year":2023,"publication_date":"2023-05-04","ids":{"openalex":"https://openalex.org/W4368362731","doi":"https://doi.org/10.1145/3576841.3589635"},"language":"en","primary_location":{"id":"doi:10.1145/3576841.3589635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3576841.3589635","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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, Tennessee, USA"],"raw_orcid":"https://orcid.org/0000-0002-4906-2179","affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, Tennessee, 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, Ohio, USA"],"raw_orcid":"https://orcid.org/0000-0002-7147-1964","affiliations":[{"raw_affiliation_string":"Parallax Advanced Research, Beavercreek, Ohio, 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, Tennessee, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8021-9923","affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, Tennessee, 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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0405708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"278","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9954000115394592,"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":0.8930863738059998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7232508659362793},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5605825185775757},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.5360676646232605},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49743130803108215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4941158592700958},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41573044657707214}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8930863738059998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232508659362793},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5605825185775757},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.5360676646232605},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49743130803108215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4941158592700958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41573044657707214},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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:10.1145/3576841.3589635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3576841.3589635","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[{"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/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/G8808569657","display_name":null,"funder_award_id":"A9550-22-1-0019","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"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/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2167489871","https://openalex.org/W3003931103","https://openalex.org/W4214717370","https://openalex.org/W4283793632"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2024136090","https://openalex.org/W2964765435","https://openalex.org/W2585069576"],"abstract_inverted_index":{"Safe":[0,15],"learning":[1,4,17,21,109],"techniques":[2],"are":[3],"frameworks":[5],"that":[6,86],"take":[7],"safety":[8,24,59,96],"into":[9],"consideration":[10],"during":[11,38],"the":[12,39,58],"training":[13],"process.":[14],"reinforcement":[16,20],"(SRL)":[18],"combines":[19],"(RL)":[22],"with":[23,98],"mechanisms":[25,97],"such":[26],"as":[27,57,79],"action":[28],"masking":[29],"and":[30],"run":[31],"time":[32],"assurance":[33],"to":[34,53,72,90,107],"protect":[35],"an":[36,50,62,75],"agent":[37],"exploration":[40,65],"of":[41],"its":[42],"environment.":[43],"This":[44],"protection,":[45],"though,":[46],"can":[47],"severely":[48],"hinder":[49],"agent's":[51],"ability":[52],"learn":[54],"optimal":[55],"policies":[56],"systems":[60],"exacerbate":[61],"already":[63],"difficult":[64],"challenge":[66],"for":[67],"RL":[68,73],"agents.":[69],"An":[70],"alternative":[71],"is":[74],"optimization":[76],"approach":[77,106],"known":[78],"genetic":[80,99],"algorithms":[81],"(GA),":[82],"which":[83],"utilize":[84],"operators":[85],"mimic":[87],"biological":[88],"evolution":[89],"evolve":[91],"better":[92],"policies.":[93],"By":[94],"combining":[95],"algorithms,":[100],"this":[101],"work":[102],"demonstrates":[103],"a":[104],"novel":[105],"safe":[108],"called":[110],"Self-Preserving":[111],"Genetic":[112],"Algorithms.":[113]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}