{"id":"https://openalex.org/W4414360559","doi":"https://doi.org/10.24963/ijcai.2025/47","title":"Counterfactual Strategies for Markov Decision Processes","display_name":"Counterfactual Strategies for Markov Decision Processes","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360559","doi":"https://doi.org/10.24963/ijcai.2025/47"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/47","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/47","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5009033094","display_name":"Paul Kobialka","orcid":"https://orcid.org/0000-0002-0635-1915"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Paul Kobialka","raw_affiliation_strings":["University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103104404","display_name":"Lina Gerlach","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lina Gerlach","raw_affiliation_strings":["RWTH Aachen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043590673","display_name":"Francesco Leofante","orcid":"https://orcid.org/0000-0001-8245-9429"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francesco Leofante","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068015318","display_name":"Erika \u00c1brah\u00e1m","orcid":"https://orcid.org/0000-0002-5647-6134"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erika \u00c1brah\u00e1m","raw_affiliation_strings":["RWTH Aachen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007372421","display_name":"Silvia Lizeth Tapia Tarifa","orcid":"https://orcid.org/0000-0001-9948-2748"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Silvia Lizeth Tapia Tarifa","raw_affiliation_strings":["University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039414480","display_name":"Einar Broch Johnsen","orcid":"https://orcid.org/0000-0001-5382-3949"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Einar Broch Johnsen","raw_affiliation_strings":["University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32416482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"412","last_page":"420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.19419999420642853,"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"}},"topics":[{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.19419999420642853,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.1850000023841858,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9381999969482422},{"id":"https://openalex.org/keywords/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.7279999852180481},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.667900025844574},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6159999966621399},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.5250999927520752},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5026000142097473},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5013999938964844}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9381999969482422},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.7279999852180481},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.667900025844574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539999842643738},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6159999966621399},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4936999976634979},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39719998836517334},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3822999894618988},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/47","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/47","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Counterfactuals":[0],"are":[1,33],"widely":[2],"used":[3],"in":[4,137],"AI":[5],"to":[6,11,17,37,70,92,96,110,119],"explain":[7],"how":[8],"minimal":[9,90],"changes":[10,91],"a":[12,18,58,83],"model\u2019s":[13],"input":[14],"can":[15],"lead":[16],"different":[19],"output.":[20],"However,":[21],"established":[22],"methods":[23],"for":[24,50],"computing":[25],"counterfactuals":[26],"typically":[27],"focus":[28],"on":[29,128],"one-step":[30],"decision-making,":[31],"and":[32,114,132],"not":[34],"directly":[35],"applicable":[36],"sequential":[38,139],"decision-making":[39,140],"tasks.":[40,141],"This":[41],"paper":[42],"fills":[43],"this":[44],"gap":[45],"by":[46],"introducing":[47],"counterfactual":[48,106,122],"strategies":[49,107],"Markov":[51],"Decision":[52],"Processes":[53],"(MDPs).":[54],"During":[55],"MDP":[56],"execution,":[57],"strategy":[59,76,95],"decides":[60],"which":[61],"of":[62],"the":[63,93,101],"enabled":[64],"actions":[65],"(with":[66],"known":[67],"probabilistic":[68],"effects)":[69],"execute":[71],"next.":[72],"Given":[73],"an":[74,79],"initial":[75,94],"that":[77,98],"reaches":[78],"undesired":[80],"outcome":[81],"with":[82],"probability":[84,99],"above":[85],"some":[86],"limit,":[87],"we":[88],"identify":[89],"reduce":[97],"below":[100],"limit.":[102],"We":[103,124],"encode":[104],"such":[105],"as":[108],"solutions":[109],"non-linear":[111],"optimization":[112],"problems,":[113],"further":[115],"extend":[116],"our":[117,126],"encoding":[118],"synthesize":[120],"diverse":[121],"strategies.":[123],"evaluate":[125],"approach":[127],"four":[129],"real-world":[130],"datasets":[131],"demonstrate":[133],"its":[134],"practical":[135],"viability":[136],"sophisticated":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}