{"id":"https://openalex.org/W2884439071","doi":"https://doi.org/10.1017/s0269888921000035","title":"Safe option-critic: learning safety in the option-critic architecture","display_name":"Safe option-critic: learning safety in the option-critic architecture","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W2884439071","doi":"https://doi.org/10.1017/s0269888921000035","mag":"2884439071"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888921000035","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888921000035","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1807.08060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010401253","display_name":"Arushi Jain","orcid":"https://orcid.org/0000-0002-3081-0421"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Arushi Jain","raw_affiliation_strings":["School of Computer Science, Mila - McGill University, Montreal, Quebec E-mail:"],"raw_orcid":"https://orcid.org/0000-0002-3081-0421","affiliations":[{"raw_affiliation_string":"School of Computer Science, Mila - McGill University, Montreal, Quebec E-mail:","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028021826","display_name":"Khimya Khetarpal","orcid":"https://orcid.org/0000-0001-9975-6438"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Khimya Khetarpal","raw_affiliation_strings":["School of Computer Science, Mila - McGill University, Montreal, Quebec E-mail:"],"raw_orcid":"https://orcid.org/0000-0001-9975-6438","affiliations":[{"raw_affiliation_string":"School of Computer Science, Mila - McGill University, Montreal, Quebec E-mail:","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["School of Computer Science, Mila - McGill University, Montreal, Quebec E-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Mila - McGill University, Montreal, Quebec E-mail:","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":2.3448,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89905244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"36","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9833999872207642,"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/computer-science","display_name":"Computer science","score":0.7741810083389282},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7639000415802002},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6410366296768188},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5981228351593018},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5626827478408813},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4775213301181793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45436835289001465},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4503244459629059},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41116422414779663},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3930004835128784},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3701511323451996},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10155525803565979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741810083389282},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7639000415802002},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6410366296768188},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5981228351593018},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5626827478408813},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4775213301181793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45436835289001465},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4503244459629059},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41116422414779663},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3930004835128784},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3701511323451996},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10155525803565979},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s0269888921000035","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888921000035","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1807.08060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.08060","pdf_url":"https://arxiv.org/pdf/1807.08060","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1807.08060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.08060","pdf_url":"https://arxiv.org/pdf/1807.08060","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W59183349","https://openalex.org/W134786152","https://openalex.org/W1492014007","https://openalex.org/W1503515926","https://openalex.org/W1506859583","https://openalex.org/W1515851193","https://openalex.org/W1518931405","https://openalex.org/W1536990779","https://openalex.org/W1551377873","https://openalex.org/W1556824961","https://openalex.org/W1585575029","https://openalex.org/W1585861384","https://openalex.org/W1592847719","https://openalex.org/W1658008008","https://openalex.org/W1845972764","https://openalex.org/W1965878388","https://openalex.org/W1978111124","https://openalex.org/W2001729196","https://openalex.org/W2020149918","https://openalex.org/W2086304253","https://openalex.org/W2088413745","https://openalex.org/W2100677568","https://openalex.org/W2101075098","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2136503687","https://openalex.org/W2143435603","https://openalex.org/W2150468603","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2158548602","https://openalex.org/W2162849300","https://openalex.org/W2163602945","https://openalex.org/W2168565265","https://openalex.org/W2169619645","https://openalex.org/W2173564293","https://openalex.org/W2197493596","https://openalex.org/W2260756217","https://openalex.org/W2267881773","https://openalex.org/W2356031020","https://openalex.org/W2442341664","https://openalex.org/W2462906003","https://openalex.org/W2498991332","https://openalex.org/W2523728418","https://openalex.org/W2566307933","https://openalex.org/W2746553466","https://openalex.org/W2750866482","https://openalex.org/W2808315817","https://openalex.org/W2809487708","https://openalex.org/W2891540084","https://openalex.org/W2963142324","https://openalex.org/W2963262099","https://openalex.org/W2963403143","https://openalex.org/W2963615220","https://openalex.org/W2963830168","https://openalex.org/W2963912551","https://openalex.org/W2964043796","https://openalex.org/W2964108826","https://openalex.org/W2964227312","https://openalex.org/W2971273232","https://openalex.org/W2997250483","https://openalex.org/W3041202696","https://openalex.org/W3103780890","https://openalex.org/W3106238320","https://openalex.org/W3128954025","https://openalex.org/W4214717370","https://openalex.org/W4245272388","https://openalex.org/W4249441547","https://openalex.org/W6629461247","https://openalex.org/W6680139899","https://openalex.org/W6680976742","https://openalex.org/W6683204974","https://openalex.org/W6683443546","https://openalex.org/W6685043521","https://openalex.org/W6693502484","https://openalex.org/W6703271639","https://openalex.org/W6706320068","https://openalex.org/W6727349600","https://openalex.org/W6752302267","https://openalex.org/W6755176883","https://openalex.org/W6766234440","https://openalex.org/W6767130282","https://openalex.org/W7071380059"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Abstract":[0],"Designing":[1],"hierarchical":[2],"reinforcement":[3],"learning":[4],"algorithms":[5],"that":[6,66,85],"exhibit":[7],"safe":[8,65,87],"behaviour":[9,63],"is":[10],"not":[11],"only":[12],"vital":[13],"for":[14],"practical":[15],"applications":[16],"but":[17],"also":[18],"facilitates":[19],"a":[20,40,62,105,125,147,170],"better":[21],"understanding":[22],"of":[23,69,78,117,142,175],"an":[24,50,82],"agent\u2019s":[25],"decisions.":[26],"We":[27,60,80,123,135],"tackle":[28],"this":[29],"problem":[30],"in":[31,75,104,120,146,172,179,184],"the":[32,76,91,109,115,121,131,137,143,158,173,185],"options":[33,88],"framework":[34],"(Sutton,":[35],"Precup":[36],"&":[37],"Singh,":[38],"1999),":[39],"particular":[41],"way":[42],"to":[43,52,93,129],"specify":[44],"temporally":[45],"abstract":[46],"actions":[47,194],"which":[48],"allow":[49],"agent":[51,92],"use":[53],"sub-policies":[54],"with":[55,72,96,181,192,196],"start":[56],"and":[57,113,139,154,165,188,195],"end":[58],"conditions.":[59],"consider":[61],"as":[64],"avoids":[67],"regions":[68],"state":[70],"space":[71],"high":[73],"uncertainty":[74,119],"outcomes":[77],"actions.":[79],"propose":[81,124],"optimization":[83],"objective":[84,102,133],"learns":[86],"by":[89],"encouraging":[90],"visit":[94],"states":[95],"higher":[97],"behavioural":[98],"consistency.":[99],"The":[100],"proposed":[101,144],"results":[103],"trade-off":[106],"between":[107],"maximizing":[108],"standard":[110],"expected":[111],"return":[112],"minimizing":[114],"effect":[116],"model":[118],"return.":[122],"policy":[126],"gradient":[127],"algorithm":[128],"optimize":[130],"constrained":[132],"function.":[134],"examine":[136],"quantitative":[138],"qualitative":[140],"behaviours":[141],"approach":[145,168],"tabular":[148],"grid":[149],"world,":[150,153],"continuous-state":[151],"puddle":[152],"three":[155],"games":[156],"from":[157],"Arcade":[159],"Learning":[160],"Environment:":[161],"Ms.":[162],"Pacman,":[163],"Amidar,":[164],"Q*Bert.":[166],"Our":[167],"achieves":[169],"reduction":[171],"variance":[174],"return,":[176],"boosts":[177],"performance":[178],"environments":[180],"intrinsic":[182],"variability":[183],"reward":[186],"structure,":[187],"compares":[189],"favourably":[190],"both":[191],"primitive":[193],"risk-neutral":[197],"options.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}