{"id":"https://openalex.org/W4392182143","doi":"https://doi.org/10.1109/icra57147.2024.10611316","title":"Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization","display_name":"Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4392182143","doi":"https://doi.org/10.1109/icra57147.2024.10611316"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.15197","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050217922","display_name":"Homayoun Honari","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Homayoun Honari","raw_affiliation_strings":["University of Victoria,Faculty of Engineering and Computer Science,Victoria,BC,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria,Faculty of Engineering and Computer Science,Victoria,BC,Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021859498","display_name":"Mehran Ghafarian Tamizi","orcid":"https://orcid.org/0000-0002-8495-0374"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mehran Ghafarian Tamizi","raw_affiliation_strings":["University of Victoria,Faculty of Engineering and Computer Science,Victoria,BC,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria,Faculty of Engineering and Computer Science,Victoria,BC,Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058540009","display_name":"Homayoun Najjaran","orcid":"https://orcid.org/0000-0002-3550-225X"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Homayoun Najjaran","raw_affiliation_strings":["University of Victoria,Faculty of Engineering and Computer Science,Victoria,BC,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria,Faculty of Engineering and Computer Science,Victoria,BC,Canada","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I212119943"],"apc_list":null,"apc_paid":null,"fwci":2.1154,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87840628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2873","last_page":"2879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9578999876976013,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9578999876976013,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.949999988079071,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T10809","display_name":"Occupational Health and Safety Research","score":0.9129999876022339,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8415637612342834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5431960225105286},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5242213010787964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4008936583995819},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2142690122127533},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12281912565231323}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8415637612342834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5431960225105286},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5242213010787964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4008936583995819},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2142690122127533},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12281912565231323}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra57147.2024.10611316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.15197","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.15197","pdf_url":"https://arxiv.org/pdf/2402.15197","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.15197","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.15197","pdf_url":"https://arxiv.org/pdf/2402.15197","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392182143.pdf","grobid_xml":"https://content.openalex.org/works/W4392182143.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2102660061","https://openalex.org/W2169206416","https://openalex.org/W2892521964","https://openalex.org/W2909414402","https://openalex.org/W2985713881","https://openalex.org/W3150718622","https://openalex.org/W3195968524","https://openalex.org/W3203657119","https://openalex.org/W3206620955","https://openalex.org/W4206497039","https://openalex.org/W6600644339","https://openalex.org/W6737893269","https://openalex.org/W6747790125","https://openalex.org/W6751725685","https://openalex.org/W6757592117","https://openalex.org/W6777159553","https://openalex.org/W6780587392","https://openalex.org/W6784630725","https://openalex.org/W6785187516","https://openalex.org/W6796274626","https://openalex.org/W6803800456","https://openalex.org/W6810739325","https://openalex.org/W6838701874","https://openalex.org/W6858013149","https://openalex.org/W6904861994"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2086122291","https://openalex.org/W1987513656","https://openalex.org/W2072376847"],"abstract_inverted_index":{"Safe":[0,37,90,199],"reinforcement":[1],"learning":[2],"(Safe":[3],"RL)":[4],"refers":[5],"to":[6,13,87,99,108,129,148,155,195],"a":[7,34,74,110,142,177],"class":[8],"of":[9,23,79,123,138,183,208],"techniques":[10],"that":[11,69,94,160],"aim":[12],"prevent":[14],"RL":[15,38,83,91,200],"algorithms":[16,92],"from":[17],"violating":[18],"constraints":[19],"in":[20,121,171,180,193,213],"the":[21,43,51,65,80,88,97,101,119,164,181,205,209],"process":[22],"decision-making":[24],"and":[25,29,57,115,151],"exploration":[26],"during":[27],"trial":[28],"error.":[30],"In":[31],"this":[32],"paper,":[33],"novel":[35],"model-free":[36],"algorithm,":[39],"formulated":[40],"based":[41],"on":[42],"multi-objective":[44],"policy":[45,52,102,147,191],"optimization":[46],"framework":[47],"is":[48,53,62,70,93],"introduced":[49],"where":[50],"optimized":[54],"towards":[55],"optimality":[56,61,116,127],"safety,":[58],"simultaneously.":[59],"The":[60,77,167,202],"achieved":[63],"by":[64],"environment":[66],"reward":[67],"function":[68],"subsequently":[71],"shaped":[72],"using":[73],"safety":[75,114,125,150,184],"critic.":[76],"advantage":[78],"Safety":[81],"Optimized":[82],"(SORL)":[84],"algorithm":[85,212],"compared":[86],"traditional":[89],"it":[95,154],"omits":[96],"need":[98],"constrain":[100],"search":[103,131],"space.":[104],"This":[105],"allows":[106,161],"SORL":[107,211],"find":[109],"natural":[111],"tradeoff":[112],"between":[113],"without":[117],"compromising":[118],"performance":[120],"terms":[122],"either":[124],"or":[126,189],"due":[128],"strict":[130],"space":[132],"constraints.":[133],"Through":[134],"our":[135],"theoretical":[136],"analysis":[137],"SORL,":[139],"we":[140],"propose":[141],"condition":[143],"for":[144,162],"SORL\u2019s":[145],"converged":[146],"guarantee":[149],"then":[152],"use":[153],"introduce":[156],"an":[157],"aggressiveness":[158],"parameter":[159],"fine-tuning":[163],"mentioned":[165],"tradeoff.":[166],"experimental":[168],"results":[169,203],"obtained":[170],"seven":[172],"different":[173,197],"robotic":[174],"environments":[175],"indicate":[176],"considerable":[178],"reduction":[179],"number":[182],"violations":[185],"along":[186],"with":[187],"higher,":[188],"competitive,":[190],"returns,":[192],"comparison":[194],"six":[196],"state-of-the-art":[198],"methods.":[201],"demonstrate":[204],"significant":[206],"superiority":[207],"proposed":[210],"safety-critical":[214],"applications.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}