{"id":"https://openalex.org/W4414360152","doi":"https://doi.org/10.24963/ijcai.2025/74","title":"Why the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement Learning","display_name":"Why the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360152","doi":"https://doi.org/10.24963/ijcai.2025/74"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/74","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/74","pdf_url":"https://www.ijcai.org/proceedings/2025/0074.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/2025/0074.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021517571","display_name":"Rui Zuo","orcid":"https://orcid.org/0000-0003-4464-3078"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Zuo","raw_affiliation_strings":["Syracuse University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syracuse University","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065073687","display_name":"Simon Khan","orcid":"https://orcid.org/0000-0002-0096-8682"},"institutions":[{"id":"https://openalex.org/I1280414376","display_name":"United States Air Force Research Laboratory","ror":"https://ror.org/02e2egq70","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280414376","https://openalex.org/I1330347796","https://openalex.org/I4210102105","https://openalex.org/I4389425425"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Khan","raw_affiliation_strings":["Air Force Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Air Force Research Laboratory","institution_ids":["https://openalex.org/I1280414376"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032942801","display_name":"Zifan Wang","orcid":"https://orcid.org/0000-0003-3394-8060"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zifan Wang","raw_affiliation_strings":["Syracuse University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syracuse University","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051693199","display_name":"Garrett E. Katz","orcid":"https://orcid.org/0000-0002-5036-8394"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garrett Ethan Katz","raw_affiliation_strings":["Syracuse University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syracuse University","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018468480","display_name":"Qinru Qiu","orcid":"https://orcid.org/0000-0003-2546-0655"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qinru Qiu","raw_affiliation_strings":["Syracuse University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syracuse University","institution_ids":["https://openalex.org/I70983195"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21183765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"655","last_page":"663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8741000294685364,"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":0.8741000294685364,"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":0.7430999875068665,"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/interpretability","display_name":"Interpretability","score":0.8844000101089478},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.7919999957084656},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6977999806404114},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4853000044822693},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3871000111103058},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.32420000433921814}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8844000101089478},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7919999957084656},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6977999806404114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6202999949455261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.608299970626831},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4853000044822693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.27790001034736633},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2671000063419342}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/74","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/74","pdf_url":"https://www.ijcai.org/proceedings/2025/0074.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.2025/74","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/74","pdf_url":"https://www.ijcai.org/proceedings/2025/0074.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/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/G4124750474","display_name":"RINGS: A Deep Reinforcement Learning Enabled Large-scale UAV Network with Distributed Navigation, Mobility Control, and Resilience","funder_award_id":"2148253","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6371787071","display_name":null,"funder_award_id":"CNS-2148253","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8289759875","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414360152.pdf","grobid_xml":"https://content.openalex.org/works/W4414360152.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,71],"(RL)":[2],"has":[3],"demonstrated":[4],"remarkable":[5],"success":[6],"in":[7,15,25,95,118],"solving":[8],"complex":[9],"decision-making":[10,27],"problems,":[11],"yet":[12],"its":[13,26],"adoption":[14],"critical":[16],"domains":[17],"is":[18,80],"hindered":[19],"by":[20,85],"the":[21,47,88,105,158,165],"lack":[22],"of":[23,50,57,69,107,120,134],"interpretability":[24],"processes.":[28],"Existing":[29],"explainable":[30],"AI":[31],"(xAI)":[32],"approaches":[33],"often":[34],"fail":[35],"to":[36,72,82],"provide":[37],"meaningful":[38],"explanations":[39,84],"for":[40,152,167],"RL":[41,74,114,161,172],"agents,":[42],"particularly":[43],"because":[44],"they":[45],"overlook":[46],"contrastive":[48,70],"nature":[49],"human":[51,132],"reasoning\u2014answering":[52],"\"why":[53],"this":[54,62],"action":[55,91],"instead":[56],"that":[58,128],"one?\"":[59],"To":[60],"address":[61],"gap,":[63],"we":[64,143],"propose":[65],"a":[66,96,100],"novel":[67],"framework":[68],"explain":[73],"selected":[75],"actions,":[76],"named":[77],"VisionMask.":[78],"VisionMask":[79,129,148],"trained":[81],"generate":[83],"explicitly":[86],"contrasting":[87],"agent's":[89],"chosen":[90],"with":[92],"alternative":[93],"actions":[94],"given":[97],"state":[98],"using":[99],"self-supervised":[101],"manner.":[102],"We":[103],"demonstrate":[104],"efficacy":[106],"our":[108],"method":[109],"through":[110],"experiments":[111],"across":[112],"diverse":[113],"environments,":[115],"evaluating":[116],"it":[117],"terms":[119],"faithfulness,":[121],"robustness":[122],"and":[123,140,162,169],"complexity.":[124],"Our":[125],"results":[126],"show":[127],"significantly":[130],"improves":[131],"understanding":[133],"agent":[135],"behavior":[136],"while":[137],"maintaining":[138],"accuracy":[139],"fidelity.":[141],"Furthermore,":[142],"present":[144],"examples":[145],"illustrating":[146],"how":[147],"can":[149],"be":[150],"used":[151],"counterfactual":[153],"analysis.":[154],"This":[155],"work":[156],"bridges":[157],"gap":[159],"between":[160],"xAI,":[163],"paving":[164],"way":[166],"safer":[168],"more":[170],"interpretable":[171],"systems.":[173]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}