{"id":"https://openalex.org/W4313005236","doi":"https://doi.org/10.1109/iros47612.2022.9981030","title":"Safety Guided Policy Optimization","display_name":"Safety Guided Policy Optimization","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4313005236","doi":"https://doi.org/10.1109/iros47612.2022.9981030"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981030","doi":"https://doi.org/10.1109/iros47612.2022.9981030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981030","pdf_url":null,"source":{"id":"https://openalex.org/S4393918188","display_name":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":"2153-0858","issn":["2153-0858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5101716360","display_name":"Dohyeong Kim","orcid":"https://orcid.org/0000-0002-3141-413X","observed_orcids":["https://orcid.org/0000-0002-3141-413X"]},"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":"Dohyeong Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826"],"raw_orcid":null,"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/A5100765696","display_name":"Yunho Kim","orcid":"https://orcid.org/0000-0001-6366-6916","observed_orcids":["https://orcid.org/0000-0001-6366-6916"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunho Kim","raw_affiliation_strings":["Robotics and Artificial Intelligence Lab, Korea Advanced Institute of Science and Technology,Department of Mechanical Engineering,Daejeon,Republic of Korea,34141"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Artificial Intelligence Lab, Korea Advanced Institute of Science and Technology,Department of Mechanical Engineering,Daejeon,Republic of Korea,34141","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604922","display_name":"Kyungjae Lee","orcid":"https://orcid.org/0000-0003-0147-2715","observed_orcids":["https://orcid.org/0000-0003-0147-2715"]},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungjae Lee","raw_affiliation_strings":["Chung-Ang University,Department of Artificial Intelligence,Seoul,Korea,06974"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Artificial Intelligence,Seoul,Korea,06974","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033764106","display_name":"Songhwai Oh","orcid":"https://orcid.org/0000-0002-9781-2018","observed_orcids":["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,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2095,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.39292485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2462","last_page":"2467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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/safe-reinforcement-learning","display_name":"safe reinforcement learning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/exploration-safety","display_name":"exploration safety","score":0.7039999961853027},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.7059999704360962},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.7730000019073486},{"id":"https://openalex.org/keywords/robot-learning","display_name":"robot learning","score":0.5299999713897705},{"id":"https://openalex.org/keywords/constraint-satisfaction","display_name":"constraint satisfaction","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C2780771206","wikidata":"https://www.wikidata.org/wiki/Q3271761","display_name":"Safeguard","level":2,"score":0.9484117031097412},{"id":"https://openalex.org/C2777381055","wikidata":"https://www.wikidata.org/wiki/Q308922","display_name":"Damages","level":2,"score":0.7293140292167664},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6997373104095459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6895147562026978},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.59647536277771},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5618461966514587},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5211103558540344},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.41587385535240173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3027183413505554},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.23942747712135315},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08622515201568604},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981030","doi":"https://doi.org/10.1109/iros47612.2022.9981030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981030","pdf_url":null,"source":{"id":"https://openalex.org/S4393918188","display_name":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":"2153-0858","issn":["2153-0858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1518931405","https://openalex.org/W1771410628","https://openalex.org/W2159307101","https://openalex.org/W2616964725","https://openalex.org/W2736601468","https://openalex.org/W2784465508","https://openalex.org/W2803543472","https://openalex.org/W2804791273","https://openalex.org/W2889347284","https://openalex.org/W2889711700","https://openalex.org/W2963184939","https://openalex.org/W2963575966","https://openalex.org/W2964161785","https://openalex.org/W2964273112","https://openalex.org/W2966735560","https://openalex.org/W2990747716","https://openalex.org/W3008953696","https://openalex.org/W3014488508","https://openalex.org/W3089710958","https://openalex.org/W3130843035","https://openalex.org/W3150718622","https://openalex.org/W3162902207","https://openalex.org/W6741002519","https://openalex.org/W6768477783"],"related_works":["https://openalex.org/W4389665627","https://openalex.org/W7167679839","https://openalex.org/W4383109037","https://openalex.org/W6948016462","https://openalex.org/W4408564563","https://openalex.org/W4402701795","https://openalex.org/W4392182143","https://openalex.org/W4386231407","https://openalex.org/W7161791241","https://openalex.org/W4403565958"],"abstract_inverted_index":{"In":[0],"reinforcement":[1],"learning":[2],"(RL),":[3],"exploration":[4,15,111],"is":[5,78,129,154],"essential":[6],"to":[7,19,36,61,63,116],"achieve":[8],"a":[9,52,162],"globally":[10],"optimal":[11],"policy":[12],"but":[13],"unconstrained":[14],"can":[16,58,123,144],"cause":[17],"damages":[18],"robots":[20,62],"and":[21,91,112,159],"nearby":[22],"people.":[23],"To":[24],"handle":[25],"this":[26],"safety":[27,43,67,178],"issue":[28],"in":[29,87,157,185],"exploration,":[30],"safe":[31,54],"RL":[32,55],"has":[33],"been":[34],"proposed":[35,76,152,170],"keep":[37],"the":[38,41,66,75,79,85,88,96,108,118,121,127,169,173],"agent":[39,122],"under":[40,65],"specified":[42],"constraints":[44,68,86,98,143,179],"while":[45,69,176],"maximizing":[46],"cumulative":[47],"rewards.":[48],"This":[49],"paper":[50],"introduces":[51],"new":[53],"method":[56,77,153,171],"which":[57],"be":[59,145],"applied":[60],"operate":[64],"learning.":[70],"The":[71,82,151,165],"key":[72],"component":[73],"of":[74],"safeguard":[80,83,109,128],"module.":[81],"predicts":[84],"near":[89],"future":[90],"corrects":[92],"actions":[93,103],"such":[94],"that":[95,168],"predicted":[97],"are":[99,104,114],"not":[100,135],"violated.":[101],"Since":[102],"safely":[105,124],"modified":[106],"by":[107],"during":[110],"policies":[113],"trained":[115],"imitate":[117],"corrected":[119],"actions,":[120],"explore.":[125],"Additionally,":[126],"sample":[130],"efficient":[131],"as":[132],"it":[133],"does":[134],"require":[136],"long":[137],"horizontal":[138],"trajectories":[139],"for":[140],"training,":[141],"so":[142],"satisfied":[146],"within":[147],"short":[148],"time":[149],"steps.":[150],"extensively":[155],"evaluated":[156],"simulation":[158],"experiments":[160],"using":[161],"real":[163],"robot.":[164],"results":[166],"show":[167],"achieves":[172],"best":[174],"performance":[175],"satisfying":[177],"with":[180,183],"minimal":[181],"interaction":[182],"environments":[184],"all":[186],"experiments.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-01-05T00:00:00"}