{"id":"https://openalex.org/W4220904784","doi":"https://doi.org/10.1007/s10994-022-06143-6","title":"Planning for potential: efficient safe reinforcement learning","display_name":"Planning for potential: efficient safe reinforcement learning","publication_year":2022,"publication_date":"2022-03-23","ids":{"openalex":"https://openalex.org/W4220904784","doi":"https://doi.org/10.1007/s10994-022-06143-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-022-06143-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06143-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06143-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06143-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082645091","display_name":"Floris den Hengst","orcid":"https://orcid.org/0000-0002-2092-9904"},"institutions":[{"id":"https://openalex.org/I4210148881","display_name":"ING Bank","ror":"https://ror.org/059et9981","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210148881"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Floris den Hengst","raw_affiliation_strings":["ING Bank N.V., Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-2092-9904","affiliations":[{"raw_affiliation_string":"ING Bank N.V., Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210148881"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015166903","display_name":"Vincent Fran\u00e7ois-Lavet","orcid":"https://orcid.org/0000-0002-8593-9740"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Vincent Fran\u00e7ois-Lavet","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044217809","display_name":"Mark Hoogendoorn","orcid":"https://orcid.org/0000-0003-3356-3574"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mark Hoogendoorn","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029130731","display_name":"Frank van Harmelen","orcid":"https://orcid.org/0000-0002-7913-0048"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Frank van Harmelen","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082645091"],"corresponding_institution_ids":["https://openalex.org/I4210148881"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":{"value":3290,"currency":"USD","value_usd":3290},"fwci":1.4675,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84332003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"111","issue":"6","first_page":"2255","last_page":"2274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9940999746322632,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.993399977684021,"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":0.7780115604400635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412176728248596},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6156297922134399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5771884322166443},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.48159167170524597},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4723050594329834},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4121952950954437},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.387823224067688},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3590877652168274},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3477925658226013},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1058485209941864}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7780115604400635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412176728248596},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6156297922134399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771884322166443},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.48159167170524597},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4723050594329834},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4121952950954437},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.387823224067688},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3590877652168274},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3477925658226013},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1058485209941864},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10994-022-06143-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06143-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06143-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:research.vu.nl:openaire/fa7580e0-f14c-464a-804f-e0c72d01c56a","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/fa7580e0-f14c-464a-804f-e0c72d01c56a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"den Hengst, F, Fran\u00e7ois-Lavet, V, Hoogendoorn, M & van Harmelen, F 2022, 'Planning for potential: efficient safe reinforcement learning', Machine Learning, vol. 111, no. 6, pp. 2255-2274. https://doi.org/10.1007/s10994-022-06143-6","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/fa7580e0-f14c-464a-804f-e0c72d01c56a","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/fa7580e0-f14c-464a-804f-e0c72d01c56a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"den Hengst, F, Fran\u00e7ois-Lavet, V, Hoogendoorn, M & van Harmelen, F 2022, 'Planning for potential: efficient safe reinforcement learning', Machine Learning, vol. 111, no. 6, pp. 2255-2274. https://doi.org/10.1007/s10994-022-06143-6","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:research.vu.nl:publications/fa7580e0-f14c-464a-804f-e0c72d01c56a","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85126907250&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"den Hengst, F, Fran\u00e7ois-Lavet, V, Hoogendoorn, M & van Harmelen, F 2022, 'Planning for potential: efficient safe reinforcement learning', Machine Learning, vol. 111, no. 6, pp. 2255-2274. https://doi.org/10.1007/s10994-022-06143-6","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10994-022-06143-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06143-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06143-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220904784.pdf","grobid_xml":"https://content.openalex.org/works/W4220904784.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W169931978","https://openalex.org/W1498432697","https://openalex.org/W1777239053","https://openalex.org/W2016206563","https://openalex.org/W2023808162","https://openalex.org/W2111316871","https://openalex.org/W2145339207","https://openalex.org/W2222789563","https://openalex.org/W2419612459","https://openalex.org/W2553882142","https://openalex.org/W2559655401","https://openalex.org/W2575705757","https://openalex.org/W2734058336","https://openalex.org/W2761873684","https://openalex.org/W2789027502","https://openalex.org/W2804948070","https://openalex.org/W2902907165","https://openalex.org/W2942608247","https://openalex.org/W2963530628","https://openalex.org/W2963575966","https://openalex.org/W2963604565","https://openalex.org/W2963778636","https://openalex.org/W2964514675","https://openalex.org/W2966537673","https://openalex.org/W2980520305","https://openalex.org/W2997022832","https://openalex.org/W3006844914","https://openalex.org/W3015197516","https://openalex.org/W3037476194","https://openalex.org/W3089636167","https://openalex.org/W3093055384","https://openalex.org/W3175871729","https://openalex.org/W4245764324","https://openalex.org/W4312313389","https://openalex.org/W6637967152","https://openalex.org/W6753925943"],"related_works":["https://openalex.org/W2288872327","https://openalex.org/W2489338148","https://openalex.org/W2124961391","https://openalex.org/W576785828","https://openalex.org/W2242084152","https://openalex.org/W2613833673","https://openalex.org/W2097931012","https://openalex.org/W4388511637","https://openalex.org/W2074131991","https://openalex.org/W2733919410"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"reinforcement":[2],"learning":[3,23,140,212],"(DRL)":[4],"has":[5],"shown":[6],"remarkable":[7],"success":[8],"in":[9,13,36,92,125,136],"artificial":[10],"domains":[11,40],"and":[12,44,87,96,112,120,144,178,194,210,213,239],"some":[14],"real-world":[15,184],"applications.":[16],"However,":[17],"substantial":[18],"challenges":[19],"remain":[20],"such":[21,41],"as":[22,42],"efficiently":[24,240],"under":[25],"safety":[26,30,153,208],"constraints.":[27,131,185],"Adherence":[28],"to":[29,52,64,72,155,218],"constraints":[31,47,111,154],"is":[32,79,205],"a":[33,57,80,89,114,123,160,164,175,179,220],"hard":[34],"requirement":[35],"many":[37],"high-impact":[38],"application":[39],"healthcare":[43],"finance.":[45],"These":[46],"are":[48],"preferably":[49],"represented":[50],"symbolically":[51,84,165],"ensure":[53],"clear":[54],"semantics":[55],"at":[56],"suitable":[58],"level":[59],"of":[60,83,109,129,159,168,226],"abstraction.":[61],"Existing":[62],"approaches":[63],"safe":[65,98],"DRL":[66],"assume":[67],"that":[68,77,202,232],"being":[69,97],"unsafe":[70],"leads":[71],"low":[73],"rewards.":[74],"We":[75,105,132,170,230],"show":[76],"this":[78,134],"special":[81],"case":[82],"constrained":[85],"RL":[86,233],"analyze":[88,106],"generic":[90],"setting":[91],"which":[93],"total":[94],"reward":[95,119],"may":[99,101],"or":[100],"not":[102],"be":[103,215,235],"correlated.":[104],"the":[107,130,157,227],"impact":[108],"symbolic":[110,150,203,244],"identify":[113],"connection":[115,135],"between":[116],"expected":[117],"future":[118],"distance":[121],"towards":[122,223],"goal":[124],"an":[126,137],"automaton":[127],"representation":[128],"use":[133],"algorithm":[138,147,191],"for":[139,189,207],"complex":[141],"behaviors":[142],"safely":[143,238],"efficiently.":[145],"This":[146],"relies":[148],"on":[149,174],"reasoning":[151,204],"over":[152],"improve":[156],"efficiency":[158,173],"subsymbolic":[161],"learner":[162,222],"with":[163,183,243],"obtained":[166],"measure":[167,171],"progress.":[169],"sample":[172],"grid":[176],"world":[177],"conversational":[180],"product":[181],"recommender":[182],"The":[186],"so-called":[187],"Planning":[188],"Potential":[190],"converges":[192],"quickly":[193],"significantly":[195],"outperforms":[196],"all":[197],"baselines.":[198],"Specifically,":[199],"we":[200],"find":[201],"necessary":[206],"during":[209],"after":[211],"can":[214,234],"effectively":[216],"used":[217],"guide":[219],"neural":[221],"promising":[224],"areas":[225],"solution":[228],"space.":[229],"conclude":[231],"applied":[236],"both":[237],"when":[241],"combined":[242],"reasoning.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2022-04-03T00:00:00"}