{"id":"https://openalex.org/W4385767976","doi":"https://doi.org/10.24963/ijcai.2023/763","title":"State-wise Safe Reinforcement Learning: A Survey","display_name":"State-wise Safe Reinforcement Learning: A Survey","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767976","doi":"https://doi.org/10.24963/ijcai.2023/763"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/763","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/763","pdf_url":"https://www.ijcai.org/proceedings/2023/0763.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0763.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112924033","display_name":"Weiye Zhao","orcid":"https://orcid.org/0000-0002-7763-3119"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiye Zhao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082052249","display_name":"Tairan He","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tairan He","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403637","display_name":"Rui Chen","orcid":"https://orcid.org/0000-0002-3690-7902"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Chen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081793768","display_name":"Tianhao Wei","orcid":"https://orcid.org/0000-0003-2505-4585"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianhao Wei","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040156274","display_name":"Changliu Liu","orcid":"https://orcid.org/0000-0002-3767-5517"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changliu Liu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":4.3564,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.9501207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6814","last_page":"6822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9865000247955322,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9746999740600586,"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":0.8827527165412903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7337664365768433},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6187835931777954},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5763041973114014},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5658901333808899},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5596515536308289},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.499622106552124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48539695143699646},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4578302502632141},{"id":"https://openalex.org/keywords/constraint-satisfaction","display_name":"Constraint satisfaction","score":0.43817421793937683},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43182986974716187},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39589300751686096},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.34683531522750854},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17637455463409424}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8827527165412903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337664365768433},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6187835931777954},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5763041973114014},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5658901333808899},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5596515536308289},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.499622106552124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48539695143699646},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4578302502632141},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.43817421793937683},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43182986974716187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39589300751686096},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.34683531522750854},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17637455463409424},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/763","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/763","pdf_url":"https://www.ijcai.org/proceedings/2023/0763.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/763","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/763","pdf_url":"https://www.ijcai.org/proceedings/2023/0763.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2570225771","display_name":null,"funder_award_id":"62176171","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4605825167","display_name":null,"funder_award_id":"U21B2040","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6584906598","display_name":null,"funder_award_id":"U19A2078","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767976.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1588424744","https://openalex.org/W1879834137","https://openalex.org/W1883346539","https://openalex.org/W2107034620","https://openalex.org/W2142742813","https://openalex.org/W2181159407","https://openalex.org/W2572663323","https://openalex.org/W2742098698","https://openalex.org/W2809299793","https://openalex.org/W2884585870","https://openalex.org/W2903938664","https://openalex.org/W2906715444","https://openalex.org/W2942919589","https://openalex.org/W2945634346","https://openalex.org/W2962779748","https://openalex.org/W2962965405","https://openalex.org/W2963517422","https://openalex.org/W2963764569","https://openalex.org/W2964022527","https://openalex.org/W2964809302","https://openalex.org/W2965624713","https://openalex.org/W2970458417","https://openalex.org/W2970947021","https://openalex.org/W3008561560","https://openalex.org/W3035477536","https://openalex.org/W3087124270","https://openalex.org/W3110446398","https://openalex.org/W3168316785","https://openalex.org/W3169978599","https://openalex.org/W3192375950","https://openalex.org/W4220873374","https://openalex.org/W4284968770","https://openalex.org/W4288097601","https://openalex.org/W4290713716","https://openalex.org/W4312658081","https://openalex.org/W4312802153","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2315999538"],"abstract_inverted_index":{"Despite":[0],"the":[1,36,46,86,98],"tremendous":[2],"success":[3],"of":[4,35,45,76,88,103,108,131],"Reinforcement":[5],"Learning":[6],"(RL)":[7],"algorithms":[8],"in":[9,26,40,50,83,106],"simulation":[10],"environments,":[11],"applying":[12],"RL":[13],"to":[14,60],"real-world":[15,41],"applications":[16,42],"still":[17],"faces":[18],"many":[19,61],"challenges.":[20],"A":[21],"major":[22],"concern":[23],"is":[24,56],"safety,":[25],"another":[27],"word,":[28],"constraint":[29],"satisfaction.":[30],"State-wise":[31,89],"constraints":[32,39,49,55,82],"are":[33],"one":[34,44],"most":[37,47],"common":[38],"and":[43,58,101,112,116,119,124,134],"challenging":[48,62],"Safe":[51],"RL.":[52,84],"Enforcing":[53],"state-wise":[54,81],"necessary":[57],"essential":[59],"tasks":[63],"such":[64],"as":[65],"autonomous":[66],"driving,":[67],"robot":[68],"manipulation.":[69],"This":[70],"paper":[71],"provides":[72],"a":[73],"comprehensive":[74],"review":[75],"existing":[77,104],"approaches":[78,105],"that":[79],"address":[80],"Under":[85],"framework":[87],"Constrained":[90],"Markov":[91],"Decision":[92],"Process":[93],"(SCMDP),":[94],"we":[95],"will":[96],"discuss":[97,135],"connections,":[99],"differences,":[100],"trade-offs":[102],"terms":[107],"(i)":[109],"safety":[110,115,121],"guarantee":[111],"scalability,":[113],"(ii)":[114],"reward":[117],"performance,":[118],"(iii)":[120],"after":[122],"convergence":[123],"during":[125],"training.":[126],"We":[127],"also":[128],"summarize":[129],"limitations":[130],"current":[132],"methods":[133],"potential":[136],"future":[137],"directions.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-30T13:55:48.251075","created_date":"2025-10-10T00:00:00"}