{"id":"https://openalex.org/W3009457412","doi":"https://doi.org/10.1109/gcce46687.2019.9014637","title":"Safe Reinforcement Learning in Continuous State Spaces","display_name":"Safe Reinforcement Learning in Continuous State Spaces","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3009457412","doi":"https://doi.org/10.1109/gcce46687.2019.9014637","mag":"3009457412"},"language":"en","primary_location":{"id":"doi:10.1109/gcce46687.2019.9014637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce46687.2019.9014637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061880909","display_name":"Takumi Umemoto","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Umemoto","raw_affiliation_strings":["Nagoya Institute of Techonology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Techonology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026933288","display_name":"Tohgoroh Matsui","orcid":"https://orcid.org/0000-0002-2002-1226"},"institutions":[{"id":"https://openalex.org/I184937672","display_name":"Chubu University","ror":"https://ror.org/02sps0775","country_code":"JP","type":"education","lineage":["https://openalex.org/I184937672"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tohgoroh Matsui","raw_affiliation_strings":["Chubu University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chubu University, Japan","institution_ids":["https://openalex.org/I184937672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113702771","display_name":"Atsuko Mutoh","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuko Mutoh","raw_affiliation_strings":["Nagoya Institute of Techonology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Techonology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066183149","display_name":"Koichi Moriyama","orcid":"https://orcid.org/0000-0003-1735-1862"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Moriyama","raw_affiliation_strings":["Nagoya Institute of Techonology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Techonology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003662586","display_name":"Nobuhiro Inuzuka","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuhiro Inuzuka","raw_affiliation_strings":["Nagoya Institute of Techonology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Techonology, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20315476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"402","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9918000102043152,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9464203119277954},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.7507182359695435},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6782051920890808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6453272700309753},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5373688340187073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.530306339263916},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4963276982307434},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.47237375378608704},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.44814324378967285},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.42509496212005615},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38519060611724854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2101612389087677},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11525177955627441},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11448732018470764},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08272239565849304}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9464203119277954},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7507182359695435},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6782051920890808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6453272700309753},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5373688340187073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.530306339263916},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4963276982307434},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.47237375378608704},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.44814324378967285},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.42509496212005615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38519060611724854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2101612389087677},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11525177955627441},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11448732018470764},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08272239565849304},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce46687.2019.9014637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce46687.2019.9014637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W129373126","https://openalex.org/W134786152","https://openalex.org/W1497976081","https://openalex.org/W1585575029","https://openalex.org/W1840625103","https://openalex.org/W1845972764","https://openalex.org/W2013406658","https://openalex.org/W2086304253","https://openalex.org/W2101075098","https://openalex.org/W2121863487","https://openalex.org/W2133632477","https://openalex.org/W2139914196","https://openalex.org/W2169206416","https://openalex.org/W2711420215","https://openalex.org/W3104013016","https://openalex.org/W3106238320","https://openalex.org/W4288079541","https://openalex.org/W6605301542"],"related_works":["https://openalex.org/W3148138296","https://openalex.org/W4294873804","https://openalex.org/W2999580272","https://openalex.org/W2350784623","https://openalex.org/W2352650970","https://openalex.org/W3127551068","https://openalex.org/W2808546214","https://openalex.org/W3203256658","https://openalex.org/W1882507001","https://openalex.org/W2367922714"],"abstract_inverted_index":{"In":[0,21,44],"using":[1],"reinforcement":[2,30,58],"learning":[3,31,59],"[1],":[4],"[2],":[5],"there":[6],"is":[7],"a":[8,54,62],"problem":[9,60],"that":[10,48],"states":[11],"are":[12],"often":[13],"provided":[14],"as":[15],"continuous":[16,26,63],"rather":[17],"than":[18,53],"discrete":[19],"values.":[20],"this":[22],"study,":[23],"we":[24,46],"applied":[25],"state":[27,64],"space":[28],"to":[29],"based":[32],"on":[33],"the":[34],"success":[35],"probability":[36],"and":[37],"return":[38],"(EQ)":[39],"[3]":[40],"of":[41],"conventional":[42,55],"research.":[43],"addition,":[45],"demonstrated":[47],"EQ":[49],"learns":[50],"more":[51],"safely":[52],"method":[56],"in":[57],"with":[61],"space.":[65]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}