{"id":"https://openalex.org/W4415209291","doi":"https://doi.org/10.1007/978-3-032-08324-1_8","title":"Counterfactual Shapley Values for Explaining Reinforcement Learning","display_name":"Counterfactual Shapley Values for Explaining Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415209291","doi":"https://doi.org/10.1007/978-3-032-08324-1_8"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-08324-1_8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-08324-1_8","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-08324-1_8.pdf","source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-08324-1_8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010583638","display_name":"Yi-Wei Shi","orcid":"https://orcid.org/0000-0003-2169-8789"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yiwei Shi","raw_affiliation_strings":["School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002349071","display_name":"Weiru Liu","orcid":"https://orcid.org/0000-0001-8356-1361"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Weiru Liu","raw_affiliation_strings":["School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010583638"],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24089772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9975000023841858,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9975000023841858,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9922999739646912,"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":0.9581999778747559,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.983299970626831},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.692300021648407},{"id":"https://openalex.org/keywords/shapley-value","display_name":"Shapley value","score":0.5522000193595886},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.43220001459121704},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.42969998717308044},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3650999963283539}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.983299970626831},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.692300021648407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5694000124931335},{"id":"https://openalex.org/C199022921","wikidata":"https://www.wikidata.org/wiki/Q240046","display_name":"Shapley value","level":3,"score":0.5522000193595886},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.39010000228881836},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.38089999556541443},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32829999923706055},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2741999924182892}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-032-08324-1_8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-08324-1_8","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-08324-1_8.pdf","source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire/464b7dab-505d-4a0f-82a5-4b2e29dbc4df","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/464b7dab-505d-4a0f-82a5-4b2e29dbc4df","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Shi, Y & Liu, W 2025, Counterfactual Shapley Values for Explaining Reinforcement Learning. in R Guidotti, U Schmid & L Longo (eds), 3rd World Conference on Explainable Artificial Intelligence. vol. II, Communications in Computer and Information Science, vol. 2577, Springer, pp. 169-193. https://doi.org/10.1007/978-3-032-08324-1_8","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1007/978-3-032-08324-1_8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-08324-1_8","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-08324-1_8.pdf","source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications in Computer and Information Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415209291.pdf","grobid_xml":"https://content.openalex.org/works/W4415209291.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W108417620","https://openalex.org/W2487898712","https://openalex.org/W3124922852","https://openalex.org/W3128395826","https://openalex.org/W3167061096","https://openalex.org/W3189931457","https://openalex.org/W3211208090","https://openalex.org/W4226275976","https://openalex.org/W4300337452","https://openalex.org/W4399375260","https://openalex.org/W4406894922","https://openalex.org/W4409369319"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"introduces":[3],"an":[4],"approach":[5,25],"based":[6,59,68],"on":[7],"Counterfactual":[8,57,66,102],"Shapley":[9,22,103],"Values,":[10],"which":[11],"enhances":[12],"explainability":[13],"in":[14,79,116],"reinforcement":[15],"learning":[16],"by":[17],"integrating":[18],"counterfactual":[19],"analysis":[20],"with":[21],"Values.":[23],"The":[24,106],"aims":[26],"to":[27,37,75],"quantify":[28],"and":[29,63,83,95],"compare":[30],"the":[31,45,56,64,77,98,101,123],"contributions":[32,80],"of":[33,47,100],"different":[34],"state":[35],"dimensions":[36],"various":[38,126],"action":[39],"choices.":[40],"To":[41],"more":[42],"accurately":[43],"analyze":[44],"impacts":[46],"these":[48],"contributions,":[49],"we":[50],"introduce":[51],"new":[52],"characteristic":[53],"value":[54],"functions,":[55],"Difference":[58,67],"Characteristic":[60,69],"Value":[61,70],"functions":[62,73],"Average":[65],"functions.":[71],"These":[72],"help":[74],"evaluate":[76],"differences":[78,124],"between":[81],"optimal":[82],"non-optimal":[84],"actions.":[85],"Experiments":[86],"across":[87,125],"several":[88],"RL":[89,118],"domains,":[90],"such":[91],"as":[92],"GridWorld,":[93],"FrozenLake,":[94],"Taxi,":[96],"demonstrate":[97],"effectiveness":[99],"Values":[104],"method.":[105],"results":[107],"show":[108],"that":[109],"this":[110],"method":[111],"not":[112],"only":[113],"improves":[114],"transparency":[115],"complex":[117],"systems":[119],"but":[120],"also":[121],"quantifies":[122],"decisions.":[127]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-16T00:00:00"}