{"id":"https://openalex.org/W2964616600","doi":"https://doi.org/10.24963/ijcai.2019/891","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":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964616600","doi":"https://doi.org/10.24963/ijcai.2019/891","mag":"2964616600"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/891","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/891","pdf_url":"https://www.ijcai.org/proceedings/2019/0891.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0891.pdf","any_repository_has_fulltext":null},"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":"Ritesh Noothigattu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"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":"Djallel Bouneffouf","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"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":"Nicholas Mattei","raw_affiliation_strings":["Tulane University, New Orleans, LA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tulane University, New Orleans, LA, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071781054","display_name":"Rachita Chandra","orcid":null},"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":"Rachita Chandra","raw_affiliation_strings":["IBM Research, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210087032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113917124","display_name":"Piyush Madan","orcid":null},"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":"Piyush Madan","raw_affiliation_strings":["IBM Research, Cambridge, MA, USA"],"raw_orcid":null,"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":"Kush R. Varshney","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"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":"Murray Campbell","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110922516","display_name":"Moninder Singh","orcid":null},"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":"Moninder Singh","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"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":"Francesca Rossi","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"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":2.3119,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91215326,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6377","last_page":"6381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9970999956130981,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9900000095367432,"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":0.8362671136856079},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.832478404045105},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7126325368881226},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6884049773216248},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5465155243873596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5131729245185852},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.45768868923187256},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.42853233218193054},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33385375142097473},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3021513819694519},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12566369771957397}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8362671136856079},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.832478404045105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126325368881226},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6884049773216248},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5465155243873596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131729245185852},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.45768868923187256},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.42853233218193054},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33385375142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3021513819694519},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12566369771957397},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/891","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/891","pdf_url":"https://www.ijcai.org/proceedings/2019/0891.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/891","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/891","pdf_url":"https://www.ijcai.org/proceedings/2019/0891.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964616600.pdf","grobid_xml":"https://content.openalex.org/works/W2964616600.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W376942001","https://openalex.org/W1999874108","https://openalex.org/W2130661992","https://openalex.org/W2240086230","https://openalex.org/W2725331431","https://openalex.org/W2794632992","https://openalex.org/W2823329128","https://openalex.org/W2856780764","https://openalex.org/W2893145483","https://openalex.org/W2909945638","https://openalex.org/W2942494530","https://openalex.org/W2963177864","https://openalex.org/W2963432546","https://openalex.org/W2964627913","https://openalex.org/W2973186106","https://openalex.org/W3119455938","https://openalex.org/W4300427736","https://openalex.org/W4307347247"],"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/W4206233823","https://openalex.org/W2494202692","https://openalex.org/W4383815550","https://openalex.org/W4312090078"],"abstract_inverted_index":{"Autonomous":[0],"cyber-physical":[1],"agents":[2,31],"play":[3],"an":[4,39],"increasingly":[5],"large":[6],"role":[7],"in":[8,16,38,104,162],"our":[9,136],"lives.":[10],"To":[11],"ensure":[12],"that":[13,28,57,142],"they":[14],"behave":[15],"ways":[17],"aligned":[18],"with":[19],"the":[20,47,87,99,108,120,143,154],"values":[21],"of":[22,50,66],"society,":[23],"we":[24],"must":[25],"develop":[26],"techniques":[27],"allow":[29],"these":[30,159],"to":[32,43,62,74,76,101,147,149],"not":[33],"only":[34],"maximize":[35,77],"their":[36],"reward":[37],"environment,":[40],"but":[41],"also":[42],"learn":[44,63,75,148],"and":[45,71,91,140,157],"follow":[46],"implicit":[48],"constraints":[49,68],"society.":[51],"We":[52,134],"detail":[53],"a":[54,64,113],"novel":[55,105],"approach":[56],"uses":[58],"inverse":[59],"reinforcement":[60,72],"learning":[61,73],"set":[65],"unspecified":[67],"from":[69,111],"demonstrations":[70],"environmental":[78],"rewards.":[79],"A":[80],"contextual":[81,95],"bandit-based":[82],"orchestrator":[83,97,121],"then":[84],"picks":[85],"between":[86],"two":[88,160],"policies:":[89],"constraint-based":[90],"environment":[92],"reward-based.":[93],"The":[94],"bandit":[96],"allows":[98],"agent":[100,144],"mix":[102,158],"policies":[103],"ways,":[106],"taking":[107],"best":[109],"actions":[110],"either":[112],"reward-maximizing":[114],"or":[115],"constrained":[116],"policy.":[117],"In":[118],"addition,":[119],"is":[122,127,145],"transparent":[123],"on":[124],"which":[125],"policy":[126],"being":[128],"employed":[129],"at":[130],"each":[131],"time":[132],"step.":[133],"test":[135],"algorithms":[137],"using":[138],"Pac-Man":[139],"show":[141],"able":[146],"act":[150,152],"optimally,":[151],"within":[153],"demonstrated":[155],"constraints,":[156],"functions":[161],"complex":[163],"ways.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}