{"id":"https://openalex.org/W3119377649","doi":"https://doi.org/10.1109/cdc42340.2020.9304411","title":"Censored Markov Decision Processes: A Framework for Safe Reinforcement Learning in Collaboration with External Systems","display_name":"Censored Markov Decision Processes: A Framework for Safe Reinforcement Learning in Collaboration with External Systems","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3119377649","doi":"https://doi.org/10.1109/cdc42340.2020.9304411","mag":"3119377649"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9304411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","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/A5088294917","display_name":"Masahiro Kohjima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Kohjima","raw_affiliation_strings":["NTT Service Evolution Laboratories, NTT Corporation, Yokosuka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Service Evolution Laboratories, NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016493447","display_name":"Masami Takahashi","orcid":"https://orcid.org/0000-0002-4152-8018"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masami Takahashi","raw_affiliation_strings":["NTT Service Evolution Laboratories, NTT Corporation, Yokosuka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Service Evolution Laboratories, NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101576701","display_name":"Hiroyuki Toda","orcid":"https://orcid.org/0000-0003-4883-527X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroyuki Toda","raw_affiliation_strings":["NTT Service Evolution Laboratories, NTT Corporation, Yokosuka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Service Evolution Laboratories, NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.18923298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"3623","last_page":"3630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9922000169754028,"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":0.9922000169754028,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11807","display_name":"Infrastructure Resilience and Vulnerability Analysis","score":0.9559999704360962,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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/markov-decision-process","display_name":"Markov decision process","score":0.9044705629348755},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8640258312225342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7100865244865417},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6113518476486206},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5748903751373291},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5434274077415466},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5076500177383423},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47699621319770813},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45603808760643005},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42131930589675903},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4140408933162689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38640230894088745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13394027948379517}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.9044705629348755},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8640258312225342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7100865244865417},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6113518476486206},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5748903751373291},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5434274077415466},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5076500177383423},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47699621319770813},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45603808760643005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42131930589675903},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4140408933162689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38640230894088745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13394027948379517},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc42340.2020.9304411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W1515851193","https://openalex.org/W1558348055","https://openalex.org/W1568042657","https://openalex.org/W1585575029","https://openalex.org/W1594216983","https://openalex.org/W1840625103","https://openalex.org/W1845972764","https://openalex.org/W1973013714","https://openalex.org/W2053572490","https://openalex.org/W2101075098","https://openalex.org/W2109910161","https://openalex.org/W2116303919","https://openalex.org/W2119567691","https://openalex.org/W2145339207","https://openalex.org/W2153947321","https://openalex.org/W2156067405","https://openalex.org/W2164479831","https://openalex.org/W2344202944","https://openalex.org/W2548134372","https://openalex.org/W2598978133","https://openalex.org/W2599292036","https://openalex.org/W2736629007","https://openalex.org/W2788005034","https://openalex.org/W2809148419","https://openalex.org/W2914154006","https://openalex.org/W2925593338","https://openalex.org/W2964273112","https://openalex.org/W3104013016","https://openalex.org/W3106238320","https://openalex.org/W4230164823","https://openalex.org/W4244668520","https://openalex.org/W4288419371","https://openalex.org/W4298023569","https://openalex.org/W6634137646","https://openalex.org/W6639175102","https://openalex.org/W6682753738","https://openalex.org/W6682802936","https://openalex.org/W6683397050","https://openalex.org/W6684037837","https://openalex.org/W6704788985","https://openalex.org/W6761021184"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W2364406457","https://openalex.org/W2173087131","https://openalex.org/W1997350370"],"abstract_inverted_index":{"The":[0],"importance":[1],"of":[2,38,59,86,114],"safe":[3],"reinforcement":[4,105],"learning":[5,106],"(safe":[6],"RL)":[7],"is":[8,82],"widely":[9],"recognized":[10],"for":[11,50,108],"enhancing":[12],"real":[13],"world":[14],"systems.":[15],"In":[16],"this":[17],"study,":[18],"we":[19],"construct":[20],"the":[21,36,57,66,77,112,115],"censored":[22],"Markov":[23,29],"decision":[24,68],"process":[25],"(CeMDP),":[26],"a":[27,83],"new":[28],"Decision":[30],"Process":[31],"(MDP)":[32],"framework":[33],"that":[34,80],"describes":[35],"interaction":[37],"environment,":[39],"learner":[40],"and":[41,74,88,104,117],"external":[42],"systems,":[43],"e.g.,":[44],"human":[45],"intervention":[46],"or":[47],"pre-designed":[48],"controller":[49],"emergency":[51],"response.":[52],"We":[53,110],"also":[54],"theoretically":[55],"analyze":[56],"relation":[58],"CeMDP":[60,81],"to":[61,101],"existing":[62],"frameworks":[63],"such":[64],"as":[65],"semi-Markov":[67],"process,":[69],"MDP":[70],"with":[71,90],"Option":[72],"(OMDP)":[73],"standard":[75],"MDP;":[76],"analysis":[78],"clarifies":[79],"special":[84],"case":[85],"OMDP":[87],"can,":[89],"environment":[91],"redefinition,":[92],"be":[93],"represented":[94],"by":[95,119],"MDP.":[96],"This":[97],"finding":[98],"allows":[99],"us":[100],"design":[102],"planning":[103],"algorithms":[107,118],"CeMDP.":[109],"confirm":[111],"validity":[113],"theory":[116],"numerical":[120],"experiments.":[121]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}