{"id":"https://openalex.org/W3123913936","doi":"https://doi.org/10.1007/978-3-030-86520-7_35","title":"Reconnaissance for Reinforcement Learning with Safety Constraints","display_name":"Reconnaissance for Reinforcement Learning with Safety Constraints","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3123913936","doi":"https://doi.org/10.1007/978-3-030-86520-7_35","mag":"3123913936"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-86520-7_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-86520-7_35","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5103253348","display_name":"Shin\u2010ichi Maeda","orcid":"https://orcid.org/0000-0002-3254-9722"},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shin-ichi Maeda","raw_affiliation_strings":["Preferred Networks, Inc., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084413468","display_name":"Hayato Watahiki","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayato Watahiki","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627878","display_name":"Yi Ouyang","orcid":"https://orcid.org/0000-0003-0556-4393"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Ouyang","raw_affiliation_strings":["Preferred Networks America, Inc., Burlingame, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Preferred Networks America, Inc., Burlingame, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004183976","display_name":"Shintarou Okada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shintarou Okada","raw_affiliation_strings":["Preferred Networks, Inc., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103751566","display_name":"Masanori Koyama","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanori Koyama","raw_affiliation_strings":["Preferred Networks, Inc., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020644058","display_name":"Prabhat Nagarajan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Prabhat Nagarajan","raw_affiliation_strings":["Preferred Networks, Inc., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Preferred Networks, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I4210166566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.3591,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50772072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"567","last_page":"582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.989799976348877,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/leverage","display_name":"Leverage (statistics)","score":0.8025946617126465},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7975000143051147},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7747377157211304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6468925476074219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5956969857215881},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5135836601257324},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5071039199829102},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.466572642326355},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4345046579837799},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42921534180641174},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4230364263057709},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4206646680831909},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39666828513145447},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3686946630477905},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3152048587799072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13580474257469177}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8025946617126465},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7975000143051147},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7747377157211304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6468925476074219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956969857215881},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5135836601257324},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5071039199829102},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.466572642326355},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4345046579837799},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42921534180641174},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4230364263057709},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4206646680831909},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39666828513145447},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3686946630477905},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3152048587799072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13580474257469177},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-86520-7_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-86520-7_35","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1506085041","https://openalex.org/W1518931405","https://openalex.org/W1561941139","https://openalex.org/W2016151598","https://openalex.org/W2033118636","https://openalex.org/W2041344731","https://openalex.org/W2053572490","https://openalex.org/W2073787051","https://openalex.org/W2084008601","https://openalex.org/W2102267552","https://openalex.org/W2116773335","https://openalex.org/W2117832167","https://openalex.org/W2121863487","https://openalex.org/W2123665586","https://openalex.org/W2145339207","https://openalex.org/W2158334497","https://openalex.org/W2163590332","https://openalex.org/W2172133054","https://openalex.org/W2213594914","https://openalex.org/W2298907094","https://openalex.org/W2341848647","https://openalex.org/W2524886531","https://openalex.org/W2576586002","https://openalex.org/W2616964725","https://openalex.org/W2756648513","https://openalex.org/W2892521964","https://openalex.org/W2913300629","https://openalex.org/W2952720101","https://openalex.org/W2962775887","https://openalex.org/W2963082979","https://openalex.org/W2963286335","https://openalex.org/W2963525569","https://openalex.org/W2964040381","https://openalex.org/W2964340170","https://openalex.org/W2968945909","https://openalex.org/W3105818906","https://openalex.org/W3106238320","https://openalex.org/W3123913936","https://openalex.org/W3157836284","https://openalex.org/W6631036983","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495","https://openalex.org/W4387506531"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}