{"id":"https://openalex.org/W2808155616","doi":"https://doi.org/10.24963/ijcai.2018/676","title":"Minimax-Regret Querying on Side Effects for Safe Optimality in Factored Markov Decision Processes","display_name":"Minimax-Regret Querying on Side Effects for Safe Optimality in Factored Markov Decision Processes","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2808155616","doi":"https://doi.org/10.24963/ijcai.2018/676","mag":"2808155616"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/676","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/676","pdf_url":"https://www.ijcai.org/proceedings/2018/0676.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0676.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100415451","display_name":"Shun Zhang","orcid":"https://orcid.org/0009-0004-3319-6596"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shun Zhang","raw_affiliation_strings":["Computer Science and Engineering, University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061747257","display_name":"Edmund H. Durfee","orcid":"https://orcid.org/0000-0002-1045-3690"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edmund H. Durfee","raw_affiliation_strings":["Computer Science and Engineering, University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103117754","display_name":"Satinder Singh","orcid":"https://orcid.org/0000-0002-8215-8295"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satinder Singh","raw_affiliation_strings":["Computer Science and Engineering, University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4867","last_page":"4873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.998199999332428,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.998199999332428,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944000244140625,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/regret","display_name":"Regret","score":0.878774106502533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777327299118042},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.7615939378738403},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.6296133995056152},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.625249981880188},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6245460510253906},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4917440712451935},{"id":"https://openalex.org/keywords/side-effect","display_name":"Side effect (computer science)","score":0.4240148365497589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4223138391971588},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3768797516822815},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34468209743499756},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.34420663118362427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11492559313774109}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.878774106502533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777327299118042},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.7615939378738403},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.6296133995056152},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.625249981880188},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6245460510253906},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4917440712451935},{"id":"https://openalex.org/C3454156","wikidata":"https://www.wikidata.org/wiki/Q1144241","display_name":"Side effect (computer science)","level":2,"score":0.4240148365497589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4223138391971588},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3768797516822815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34468209743499756},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34420663118362427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11492559313774109},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/676","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/676","pdf_url":"https://www.ijcai.org/proceedings/2018/0676.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/676","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/676","pdf_url":"https://www.ijcai.org/proceedings/2018/0676.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4818823069","display_name":null,"funder_award_id":"FA9550-15-1-0039","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G7090116110","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"}],"funders":[{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808155616.pdf","grobid_xml":"https://content.openalex.org/works/W2808155616.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W9932698","https://openalex.org/W15411808","https://openalex.org/W202180931","https://openalex.org/W1493096714","https://openalex.org/W1541317966","https://openalex.org/W1749432972","https://openalex.org/W1845972764","https://openalex.org/W1965878388","https://openalex.org/W1991185257","https://openalex.org/W2061504687","https://openalex.org/W2146771148","https://openalex.org/W2228499913","https://openalex.org/W2283935042","https://openalex.org/W2405100124","https://openalex.org/W2409942531","https://openalex.org/W2462906003","https://openalex.org/W2619787335","https://openalex.org/W2621205314","https://openalex.org/W2758935952","https://openalex.org/W2952232073","https://openalex.org/W2952720101","https://openalex.org/W2962799618","https://openalex.org/W2962803570","https://openalex.org/W4293545785","https://openalex.org/W4295264289","https://openalex.org/W4297780563","https://openalex.org/W4300427736"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W2751383663","https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W1850488217","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W1970303738"],"abstract_inverted_index":{"As":[0],"it":[1,93,105],"achieves":[2],"a":[3,57,77,108],"goal":[4],"on":[5],"behalf":[6],"of":[7,22],"its":[8,23,30,116],"human":[9],"user,":[10],"an":[11],"autonomous":[12],"agent's":[13],"actions":[14],"may":[15],"have":[16],"side":[17,64],"effects":[18,65],"that":[19,27,34,60,92],"change":[20,44],"features":[21,45,91],"environment":[24],"in":[25],"ways":[26],"negatively":[28],"surprise":[29],"user.":[31],"An":[32],"agent":[33,69,84],"can":[35],"be":[36],"trusted":[37],"to":[38,85],"operate":[39],"safely":[40],"should":[41],"thus":[42],"only":[43],"the":[46,68,83,88,123],"user":[47,89],"has":[48],"explicitly":[49,95],"permitted.":[50],"We":[51,99],"formalize":[52],"this":[53],"problem,":[54],"and":[55,112],"develop":[56],"planning":[58],"algorithm":[59],"avoids":[61],"potentially":[62],"negative":[63],"given":[66],"what":[67],"knows":[70],"about":[71,90],"(un)changeable":[72],"features.":[73],"Further,":[74],"we":[75],"formulate":[76],"provably":[78],"minimax-regret":[79],"querying":[80],"strategy":[81],"for":[82],"selectively":[86],"ask":[87],"hasn't":[94],"been":[96],"told":[97],"about.":[98],"empirically":[100],"show":[101],"how":[102,113],"much":[103,114],"faster":[104],"is":[106],"than":[107,119],"more":[109],"exhaustive":[110],"approach":[111],"better":[115],"queries":[117],"are":[118],"those":[120],"found":[121],"by":[122],"best":[124],"known":[125],"heuristic.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}