{"id":"https://openalex.org/W4405785596","doi":"https://doi.org/10.1109/iros58592.2024.10801577","title":"Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards","display_name":"Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785596","doi":"https://doi.org/10.1109/iros58592.2024.10801577"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5101887822","display_name":"Hyeokjin Kwon","orcid":"https://orcid.org/0000-0001-9468-034X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyeokjin Kwon","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in Artificial Intelligence and ASRI,Seoul,Korea,08826"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in Artificial Intelligence and ASRI,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024425360","display_name":"Gunmin Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunmin Lee","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705399","display_name":"Junseo Lee","orcid":"https://orcid.org/0009-0009-4953-1383"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junseo Lee","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in Artificial Intelligence and ASRI,Seoul,Korea,08826"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in Artificial Intelligence and ASRI,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033764106","display_name":"Songhwai Oh","orcid":"https://orcid.org/0000-0002-9781-2018"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Songhwai Oh","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in Artificial Intelligence and ASRI,Seoul,Korea,08826"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in Artificial Intelligence and ASRI,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101887822"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78129292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2893","last_page":"2898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8650000095367432,"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":0.8650000095367432,"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":0.7702513933181763},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7291812896728516},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.692106306552887},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6574323177337646},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6545277833938599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4991331100463867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4431365430355072},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15972155332565308},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10061526298522949}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7702513933181763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291812896728516},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.692106306552887},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6574323177337646},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6545277833938599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4991331100463867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4431365430355072},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15972155332565308},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10061526298522949},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2963669336","https://openalex.org/W3127561923","https://openalex.org/W3133456577","https://openalex.org/W3145799606","https://openalex.org/W3203076355","https://openalex.org/W3208122016","https://openalex.org/W4206663383","https://openalex.org/W4240805545","https://openalex.org/W4285066191","https://openalex.org/W4292347911","https://openalex.org/W4385416220","https://openalex.org/W4389666601","https://openalex.org/W6638018090","https://openalex.org/W6640174482","https://openalex.org/W6674884181","https://openalex.org/W6684338915","https://openalex.org/W6718092244","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6779381009","https://openalex.org/W6794641712","https://openalex.org/W6798202049","https://openalex.org/W6848993989"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2665305151"],"abstract_inverted_index":{"In":[0],"the":[1,48,86,100,107,112,131,154],"realm":[2,155],"of":[3,62,92,156],"autonomous":[4,160],"agents,":[5],"ensuring":[6],"safety":[7,27,96,108],"and":[8,12,71,111,124,158],"reliability":[9],"in":[10,33,103,146,153],"complex":[11,39],"dynamic":[13],"environments":[14,36],"remains":[15],"a":[16,55,79],"paramount":[17],"challenge.":[18],"Safe":[19],"reinforcement":[20],"learning":[21],"addresses":[22],"these":[23,44],"concerns":[24],"by":[25,122,128],"introducing":[26],"constraints,":[28],"but":[29],"still":[30],"faces":[31],"challenges":[32],"navigating":[34],"intricate":[35],"such":[37],"as":[38],"driving":[40],"situations.":[41],"To":[42],"overcome":[43],"challenges,":[45],"we":[46,142],"present":[47],"safe":[49,72,157],"constraint":[50,80,126],"reward":[51,81,93],"(Safe":[52],"CoR)":[53],"framework,":[54],"novel":[56],"method":[57],"that":[58],"utilizes":[59],"two":[60],"types":[61],"expert":[63,65,73],"demonstrations\u2014reward":[64],"demonstrations":[66,74],"focusing":[67],"on":[68,130],"performance":[69,90,121],"optimization":[70],"prioritizing":[75],"safety.":[76],"By":[77],"exploiting":[78],"(CoR),":[82],"our":[83],"framework":[84,102,118],"guides":[85],"agent":[87],"to":[88,150],"balance":[89],"goals":[91],"sum":[94],"with":[95],"constraints.":[97],"We":[98],"test":[99],"proposed":[101,117],"diverse":[104],"environments,":[105],"including":[106],"gym,":[109],"metadrive,":[110],"real-world":[113,132,147],"Jackal":[114,133],"platform.":[115],"Our":[116],"improves":[119],"algorithm":[120],"39%":[123],"reduces":[125],"violations":[127],"88%":[129],"platform,":[134],"highlighting":[135],"its":[136],"effectiveness.":[137],"Through":[138],"this":[139],"innovative":[140],"approach,":[141],"expect":[143],"significant":[144],"advancements":[145],"performance,":[148],"leading":[149],"transformative":[151],"effects":[152],"reliable":[159],"agents.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}