{"id":"https://openalex.org/W4414360354","doi":"https://doi.org/10.24963/ijcai.2025/561","title":"Counterfactual Explanations for Continuous Action Reinforcement Learning","display_name":"Counterfactual Explanations for Continuous Action Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360354","doi":"https://doi.org/10.24963/ijcai.2025/561"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/561","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/561","pdf_url":"https://www.ijcai.org/proceedings/2025/0561.pdf","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":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0561.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109643808","display_name":"Shuyang Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuyang Dong","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033834190","display_name":"Shangtong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shangtong Zhang","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050527785","display_name":"Feng Lu","orcid":"https://orcid.org/0000-0001-9064-7964"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Feng","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":1.6289,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84917104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5039","last_page":"5046"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9818000197410583,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9818000197410583,"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":0.9800999760627747,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9056000113487244,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9384999871253967},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7548999786376953},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6657000184059143},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6223000288009644},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6200000047683716},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5436999797821045}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9384999871253967},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7548999786376953},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6657000184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6247000098228455},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6200000047683716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5544000267982483},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4359000027179718},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.26159998774528503},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/561","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/561","pdf_url":"https://www.ijcai.org/proceedings/2025/0561.pdf","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":{"id":"doi:10.24963/ijcai.2025/561","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/561","pdf_url":"https://www.ijcai.org/proceedings/2025/0561.pdf","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7839859305","display_name":"CAREER: Formal Methods for Human-Cyber-Physical Systems","funder_award_id":"1942836","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8404007027","display_name":"Collaborative Research: DASS: Accountable Software Systems for Safety-Critical Applications","funder_award_id":"2131511","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414360354.pdf","grobid_xml":"https://content.openalex.org/works/W4414360354.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"shown":[4],"great":[5],"promise":[6],"in":[7,55,93,97],"domains":[8],"like":[9],"healthcare":[10],"and":[11,83,103,110,118],"robotics":[12],"but":[13,39],"often":[14],"struggles":[15],"with":[16],"adoption":[17],"due":[18],"to":[19,90],"its":[20],"lack":[21],"of":[22,112],"interpretability.":[23],"Counterfactual":[24],"explanations,":[25],"which":[26],"address":[27],"``what":[28],"if\u201d":[29],"scenarios,":[30],"provide":[31],"a":[32,48,77],"promising":[33],"avenue":[34],"for":[35,42,51,80,85],"understanding":[36],"RL":[37,58,99,120],"decisions":[38],"remain":[40],"underexplored":[41],"continuous":[43,56,81],"action":[44,57,62],"spaces.":[45],"We":[46],"propose":[47],"novel":[49],"approach":[50,75],"generating":[52],"counterfactual":[53],"explanations":[54],"by":[59],"computing":[60],"alternative":[61],"sequences":[63],"that":[64],"improve":[65],"outcomes":[66],"while":[67],"minimizing":[68],"deviations":[69],"from":[70],"the":[71,107],"original":[72],"sequence.":[73],"Our":[74],"leverages":[76],"distance":[78],"metric":[79],"actions":[82],"accounts":[84],"constraints":[86],"such":[87],"as":[88],"adhering":[89],"predefined":[91],"policies":[92],"specific":[94],"states.":[95],"Evaluations":[96],"two":[98],"domains,":[100],"Diabetes":[101],"Control":[102],"Lunar":[104],"Lander,":[105],"demonstrate":[106],"effectiveness,":[108],"efficiency,":[109],"generalization":[111],"our":[113],"approach,":[114],"enabling":[115],"more":[116],"interpretable":[117],"trustworthy":[119],"applications.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}