{"id":"https://openalex.org/W3158410831","doi":"https://doi.org/10.1109/tai.2024.3363122","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","display_name":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","publication_year":2024,"publication_date":"2024-02-16","ids":{"openalex":"https://openalex.org/W3158410831","doi":"https://doi.org/10.1109/tai.2024.3363122","mag":"3158410831"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2024.3363122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3363122","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-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/A5081575225","display_name":"Md Sultan Al Nahian","orcid":"https://orcid.org/0009-0001-8016-806X"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Sultan al Nahian","raw_affiliation_strings":["University of Kentucky, Lexington, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030393924","display_name":"Spencer Frazier","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spencer Frazier","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061883150","display_name":"Mark Riedl","orcid":"https://orcid.org/0000-0001-5283-6588"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Riedl","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047163199","display_name":"Brent Harrison","orcid":"https://orcid.org/0000-0002-1301-5928"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brent Harrison","raw_affiliation_strings":["University of Kentucky, Lexington, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081575225"],"corresponding_institution_ids":["https://openalex.org/I143302722"],"apc_list":null,"apc_paid":null,"fwci":1.3901,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82588881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"5","issue":"7","first_page":"3350","last_page":"3361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9646999835968018,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12761","display_name":"Data Stream Mining Techniques","score":0.9627000093460083,"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/normative","display_name":"Normative","score":0.7459812760353088},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.685472846031189},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6821526885032654},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5262840390205383},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.451036274433136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3254125118255615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30984702706336975},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.2778692841529846},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14908644556999207},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.10292717814445496},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04789012670516968}],"concepts":[{"id":"https://openalex.org/C44725695","wikidata":"https://www.wikidata.org/wiki/Q288156","display_name":"Normative","level":2,"score":0.7459812760353088},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.685472846031189},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6821526885032654},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5262840390205383},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.451036274433136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3254125118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30984702706336975},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2778692841529846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14908644556999207},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.10292717814445496},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04789012670516968}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2024.3363122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3363122","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G8345472565","display_name":null,"funder_award_id":"1849231","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1583953806","https://openalex.org/W1940872118","https://openalex.org/W1999874108","https://openalex.org/W2098441518","https://openalex.org/W2143063108","https://openalex.org/W2240086230","https://openalex.org/W2277018427","https://openalex.org/W2290053245","https://openalex.org/W2342281051","https://openalex.org/W2401592218","https://openalex.org/W2434014514","https://openalex.org/W2591957724","https://openalex.org/W2740721704","https://openalex.org/W2754794180","https://openalex.org/W2782698114","https://openalex.org/W2794632992","https://openalex.org/W2810346659","https://openalex.org/W2891217993","https://openalex.org/W2896457183","https://openalex.org/W2909911836","https://openalex.org/W2938303713","https://openalex.org/W2947619145","https://openalex.org/W2949801941","https://openalex.org/W2963088995","https://openalex.org/W2963341956","https://openalex.org/W2964043796","https://openalex.org/W2964110616","https://openalex.org/W2970597249","https://openalex.org/W2973379954","https://openalex.org/W2992807692","https://openalex.org/W2996681978","https://openalex.org/W2997764164","https://openalex.org/W3002728196","https://openalex.org/W3004725011","https://openalex.org/W3034344071","https://openalex.org/W3035348754","https://openalex.org/W3052814785","https://openalex.org/W3094404987","https://openalex.org/W3100826325","https://openalex.org/W3111265093","https://openalex.org/W3207835719","https://openalex.org/W3215312454","https://openalex.org/W4289360648","https://openalex.org/W6638591638","https://openalex.org/W6640362995","https://openalex.org/W6674812091","https://openalex.org/W6694688768","https://openalex.org/W6696265566","https://openalex.org/W6713055699","https://openalex.org/W6714580625","https://openalex.org/W6718092244","https://openalex.org/W6729863922","https://openalex.org/W6731433928","https://openalex.org/W6734502593","https://openalex.org/W6739585900","https://openalex.org/W6740734016","https://openalex.org/W6744338129","https://openalex.org/W6746721349","https://openalex.org/W6749544332","https://openalex.org/W6755207826","https://openalex.org/W6755773820","https://openalex.org/W6763701032","https://openalex.org/W6767858076","https://openalex.org/W6772190580","https://openalex.org/W6802529681"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1989297139","https://openalex.org/W2342143608","https://openalex.org/W2496755843","https://openalex.org/W1977959518","https://openalex.org/W4213090964","https://openalex.org/W2038908348","https://openalex.org/W892323923"],"abstract_inverted_index":{"Value":[0],"alignment":[1],"is":[2,49,119],"a":[3,35,41,52,84,126],"property":[4],"of":[5,93],"intelligent":[6],"agents":[7,124],"wherein":[8],"they":[9],"solely":[10],"pursue":[11],"non-harmful":[12],"behaviors":[13],"or":[14,77],"human-beneficial":[15],"goals.":[16],"We":[17,79,107],"introduce":[18],"an":[19,29],"approach":[20],"to":[21,72,122,133,138],"value-aligned":[22,53],"reinforcement":[23],"learning,":[24],"in":[25,140],"which":[26],"we":[27,57],"train":[28,58],"agent":[30],"with":[31,125],"two":[32,91],"reward":[33,39,48,94],"signals:":[34],"standard":[36],"task":[37,127,137],"performance":[38],"plus":[40],"normative":[42,46,76,141],"behavior":[43,47],"reward.":[44],"The":[45],"derived":[50],"from":[51,135],"prior":[54],"model":[55],"that":[56,98],"using":[59],"naturally":[60],"occurring":[61],"stories.":[62],"These":[63],"stories":[64],"encode":[65],"societal":[66],"norms":[67],"and":[68,95,102],"can":[69,88],"be":[70],"used":[71],"classify":[73],"text":[74],"as":[75,104,128,130],"non-normative.":[78],"show":[80],"how":[81],"variations":[82],"on":[83,112],"policy":[85],"shaping":[86],"technique":[87,111],"balance":[89],"these":[90],"sources":[92],"produce":[96],"policies":[97],"are":[99],"both":[100],"effective":[101],"perceived":[103],"more":[105],"normative.":[106],"test":[108],"our":[109],"value-alignment":[110],"three":[113],"interactive":[114],"text-based":[115],"worlds;":[116],"each":[117],"world":[118],"designed":[120],"specifically":[121],"challenge":[123],"well":[129],"provide":[131],"opportunities":[132],"deviate":[134],"the":[136],"engage":[139],"and/or":[142],"altruistic":[143],"behavior.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}