{"id":"https://openalex.org/W2973186106","doi":"https://doi.org/10.1147/jrd.2019.2940428","title":"Teaching AI agents ethical values using reinforcement learning and policy orchestration","display_name":"Teaching AI agents ethical values using reinforcement learning and policy orchestration","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2973186106","doi":"https://doi.org/10.1147/jrd.2019.2940428","mag":"2973186106"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2019.2940428","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2019.2940428","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","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/A5040419676","display_name":"Ritesh Noothigattu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R. Noothigattu","raw_affiliation_strings":["Carnegie Mellon University Pittsburgh PA USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh PA USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055394860","display_name":"Djallel Bouneffouf","orcid":"https://orcid.org/0000-0003-3342-7513"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Bouneffouf","raw_affiliation_strings":["IBM Research , Yorktown Heights, NY , USA"],"affiliations":[{"raw_affiliation_string":"IBM Research , Yorktown Heights, NY , USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025297787","display_name":"Nicholas Mattei","orcid":"https://orcid.org/0000-0002-3569-4335"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Mattei","raw_affiliation_strings":["Tulane University, New Orleans LA, USA"],"affiliations":[{"raw_affiliation_string":"Tulane University, New Orleans LA, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070117215","display_name":"Ram Chandra","orcid":"https://orcid.org/0000-0003-0880-1876"},"institutions":[{"id":"https://openalex.org/I4210087032","display_name":"Cambridge Scientific (United States)","ror":"https://ror.org/001s4dh65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Chandra","raw_affiliation_strings":["IBM Research, Cambridge , MA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Cambridge , MA, USA","institution_ids":["https://openalex.org/I4210087032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091293680","display_name":"Pankaj Madan","orcid":"https://orcid.org/0000-0002-4648-9863"},"institutions":[{"id":"https://openalex.org/I4210087032","display_name":"Cambridge Scientific (United States)","ror":"https://ror.org/001s4dh65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Madan","raw_affiliation_strings":["IBM Research, Cambridge , MA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Cambridge , MA, USA","institution_ids":["https://openalex.org/I4210087032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015286159","display_name":"Kush R. Varshney","orcid":"https://orcid.org/0000-0002-7376-5536"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. R. Varshney","raw_affiliation_strings":["IBM Research , Yorktown Heights, NY , USA"],"affiliations":[{"raw_affiliation_string":"IBM Research , Yorktown Heights, NY , USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045892503","display_name":"Murray Campbell","orcid":"https://orcid.org/0000-0001-8158-894X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Campbell","raw_affiliation_strings":["IBM Research , Yorktown Heights, NY , USA"],"affiliations":[{"raw_affiliation_string":"IBM Research , Yorktown Heights, NY , USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037536909","display_name":"Manjeet Singh","orcid":"https://orcid.org/0000-0001-9558-4640"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Singh","raw_affiliation_strings":["IBM Research , Yorktown Heights, NY , USA"],"affiliations":[{"raw_affiliation_string":"IBM Research , Yorktown Heights, NY , USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000527699","display_name":"Francesca Rossi","orcid":"https://orcid.org/0000-0001-8898-219X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F. Rossi","raw_affiliation_strings":["IBM Research , Yorktown Heights, NY , USA"],"affiliations":[{"raw_affiliation_string":"IBM Research , Yorktown Heights, NY , USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5040419676"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.6045,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.92224419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"63","issue":"4/5","first_page":"2:1","last_page":"2:9"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9957000017166138,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.8320232629776001},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8008828163146973},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6960188150405884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6625634431838989},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5452258586883545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4799421429634094},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16138991713523865},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07218223810195923}],"concepts":[{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.8320232629776001},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8008828163146973},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6960188150405884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6625634431838989},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5452258586883545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4799421429634094},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16138991713523865},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07218223810195923},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1147/jrd.2019.2940428","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2019.2940428","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W376942001","https://openalex.org/W1999874108","https://openalex.org/W2130661992","https://openalex.org/W2240086230","https://openalex.org/W2241687965","https://openalex.org/W2346475268","https://openalex.org/W2462906003","https://openalex.org/W2466381818","https://openalex.org/W2519411794","https://openalex.org/W2579124618","https://openalex.org/W2725331431","https://openalex.org/W2758041078","https://openalex.org/W2772337934","https://openalex.org/W2823329128","https://openalex.org/W2856780764","https://openalex.org/W2883535494","https://openalex.org/W2893145483","https://openalex.org/W2909945638","https://openalex.org/W2942494530","https://openalex.org/W2951932496","https://openalex.org/W2963177864","https://openalex.org/W2963432546","https://openalex.org/W2964627913","https://openalex.org/W3119455938","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4294624294","https://openalex.org/W4299286629","https://openalex.org/W6613001717","https://openalex.org/W6684588631","https://openalex.org/W6705404873","https://openalex.org/W6718836005","https://openalex.org/W6726651112","https://openalex.org/W6744508736","https://openalex.org/W6746621100","https://openalex.org/W6746721349","https://openalex.org/W6747985145","https://openalex.org/W6749992176","https://openalex.org/W6753499099","https://openalex.org/W6755109443","https://openalex.org/W6761779590"],"related_works":["https://openalex.org/W79913212","https://openalex.org/W2094884983","https://openalex.org/W2378898096","https://openalex.org/W560952460","https://openalex.org/W2290927522","https://openalex.org/W4283579741","https://openalex.org/W3066706303","https://openalex.org/W876159576","https://openalex.org/W2943612818","https://openalex.org/W1994346114"],"abstract_inverted_index":{"Autonomous":[0],"cyber-physical":[1],"agents":[2,31],"play":[3],"an":[4,39],"increasingly":[5],"large":[6],"role":[7],"in":[8,16,38,103,161],"our":[9,135],"lives.":[10],"To":[11],"ensure":[12],"that":[13,28,57,141],"they":[14],"behave":[15],"ways":[17],"aligned":[18],"with":[19],"the":[20,47,86,98,107,119,142,153],"values":[21],"of":[22,50,66],"society,":[23],"we":[24],"must":[25],"develop":[26],"techniques":[27],"allow":[29],"these":[30,158],"to":[32,43,62,74,76,100,146,148],"not":[33],"only":[34],"maximize":[35,77],"their":[36],"reward":[37],"environment,":[40],"but":[41],"also":[42],"learn":[44,63,75,147],"and":[45,71,90,139,156],"follow":[46],"implicit":[48],"constraints":[49,68],"society.":[51],"We":[52,133],"detail":[53],"a":[54,64,112],"novel":[55,104],"approach":[56],"uses":[58],"inverse":[59],"reinforcement":[60,72],"learning":[61,73],"set":[65],"unspecified":[67],"from":[69,110],"demonstrations":[70],"environmental":[78],"rewards.":[79],"A":[80],"contextual-bandit-based":[81],"orchestrator":[82,96,120],"then":[83],"picks":[84],"between":[85],"two":[87,159],"policies:":[88],"constraint-based":[89],"environment":[91],"reward-based.":[92],"The":[93],"contextual":[94],"bandit":[95],"allows":[97],"agent":[99,143],"mix":[101,157],"policies":[102],"ways,":[105],"taking":[106],"best":[108],"actions":[109],"either":[111],"reward-maximizing":[113],"or":[114],"constrained":[115],"policy.":[116],"In":[117],"addition,":[118],"is":[121,126,144],"transparent":[122],"on":[123],"which":[124],"policy":[125],"being":[127],"employed":[128],"at":[129],"each":[130],"time":[131],"step.":[132],"test":[134],"algorithms":[136],"using":[137],"Pac-Man":[138],"show":[140],"able":[145],"act":[149,151],"optimally,":[150],"within":[152],"demonstrated":[154],"constraints,":[155],"functions":[160],"complex":[162],"ways.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}