{"id":"https://openalex.org/W4404553244","doi":"https://doi.org/10.1145/3687272.3688324","title":"Semifactual Explanations for Reinforcement Learning","display_name":"Semifactual Explanations for Reinforcement Learning","publication_year":2024,"publication_date":"2024-11-20","ids":{"openalex":"https://openalex.org/W4404553244","doi":"https://doi.org/10.1145/3687272.3688324"},"language":"en","primary_location":{"id":"doi:10.1145/3687272.3688324","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3687272.3688324","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3687272.3688324?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3687272.3688324?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029228044","display_name":"Jasmina Gajcin","orcid":"https://orcid.org/0000-0002-8731-1236"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Jasmina Gajcin","raw_affiliation_strings":["School of Computer Science and Statistics, Trinity College Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-8731-1236","affiliations":[{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047053071","display_name":"Jovan Jeromela","orcid":"https://orcid.org/0000-0003-3272-9114"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Jovan Jeromela","raw_affiliation_strings":["School of Computer Science and Statistics, Trinity College Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0003-3272-9114","affiliations":[{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059738292","display_name":"Ivana Duspari\u0107","orcid":"https://orcid.org/0000-0003-0621-5400"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ivana Dusparic","raw_affiliation_strings":["School of Computer Science and Statistics, Trinity College Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0003-0621-5400","affiliations":[{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9936000108718872,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9936000108718872,"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":0.9804999828338623,"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/T10260","display_name":"Software Engineering Research","score":0.9667999744415283,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7794177532196045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7145169973373413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4936617314815521}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7794177532196045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145169973373413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4936617314815521}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3687272.3688324","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3687272.3688324","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3687272.3688324?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3687272.3688324","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3687272.3688324","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3687272.3688324?download=true","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2394637485","display_name":"SFI Centre for Research Training in Artificial Intelligence","funder_award_id":"18/CRT/6223","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G3862017314","display_name":null,"funder_award_id":"18/CRT/6223; 21/FFP-A/8957","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404553244.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2110884135","https://openalex.org/W2118958845","https://openalex.org/W2126105956","https://openalex.org/W2493343568","https://openalex.org/W2622408375","https://openalex.org/W2765204106","https://openalex.org/W2963641083","https://openalex.org/W3085543735","https://openalex.org/W3100789280","https://openalex.org/W3124922852","https://openalex.org/W4214717370","https://openalex.org/W4298235707","https://openalex.org/W4310445610","https://openalex.org/W4360826797","https://openalex.org/W4385763726","https://openalex.org/W4385767379","https://openalex.org/W4389282384","https://openalex.org/W4389282388","https://openalex.org/W4389282400","https://openalex.org/W4389282404","https://openalex.org/W4391897126","https://openalex.org/W4393146589"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"is":[3,43],"a":[4,135,209],"learning":[5,21],"paradigm":[6],"in":[7,110,115,155,170,176],"which":[8],"the":[9,25,38,73,93,99,103,125,163,174,193,214,221],"agent":[10],"learns":[11],"from":[12],"its":[13],"environment":[14],"through":[15],"trial":[16],"and":[17,51,101,112,157,161,181,197,207],"error.":[18],"Deep":[19],"reinforcement":[20],"(DRL)":[22],"algorithms":[23,165,175],"represent":[24,192],"agent\u2019s":[26,194,222],"policies":[27],"using":[28],"neural":[29],"networks,":[30],"making":[31],"their":[32],"decisions":[33,126],"difficult":[34],"to":[35,45,60,84,86,123,138,190,202,212],"interpret.":[36],"Explaining":[37],"behaviour":[39],"of":[40,95,105,127,151,217,220],"DRL":[41],"agents":[42],"necessary":[44],"advance":[46],"user":[47,210],"trust,":[48],"increase":[49],"engagement,":[50],"facilitate":[52],"integration":[53],"with":[54],"real-life":[55],"tasks.":[56],"Semifactual":[57],"explanations":[58,141,154,169,219],"aim":[59],"explain":[61,124],"an":[62],"outcome":[63,100],"by":[64,147],"providing":[65],"\u201ceven":[66,71],"if\u201d":[67],"scenarios,":[68],"such":[69],"as":[70,78],"if":[72],"car":[74],"were":[75],"moving":[76],"twice":[77],"slowly,":[79],"it":[80],"would":[81],"still":[82],"have":[83,119],"swerve":[85],"avoid":[87],"crashing\u201d.":[88],"Semifactuals":[89],"help":[90],"users":[91],"understand":[92],"effects":[94],"different":[96],"factors":[97],"on":[98],"support":[102],"optimisation":[104],"resources.":[106],"While":[107],"extensively":[108],"studied":[109],"psychology":[111],"even":[113],"utilised":[114],"supervised":[116],"learning,":[117],"semifactuals":[118,186],"not":[120],"been":[121],"used":[122],"RL":[128,143,156,179],"systems.":[129],"In":[130],"this":[131],"work,":[132],"we":[133,205],"develop":[134],"first":[136,164],"approach":[137],"generating":[139,167],"semifactual":[140,153,168,218],"for":[142,166],"agents.":[144],"We":[145,172],"start":[146],"defining":[148],"five":[149],"properties":[150],"desirable":[152],"then":[158],"introducing":[159],"SGRL-Rewind":[160],"SGRL-Advance,":[162],"RL.":[171],"evaluate":[173],"two":[177],"standard":[178],"environments":[180],"find":[182],"that":[183,187],"they":[184],"generate":[185],"are":[188,198],"easier":[189],"reach,":[191],"policy":[195],"better,":[196],"more":[199],"diverse":[200],"compared":[201],"baselines.":[203],"Lastly,":[204],"conduct":[206],"analyse":[208],"study":[211],"assess":[213],"participant\u2019s":[215],"perception":[216],"actions.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}