{"id":"https://openalex.org/W4297679012","doi":"https://doi.org/10.1145/3549737.3549808","title":"Tutorial on Explainable Deep Reinforcement Learning: One framework, three paradigms and many challenges.","display_name":"Tutorial on Explainable Deep Reinforcement Learning: One framework, three paradigms and many challenges.","publication_year":2022,"publication_date":"2022-09-07","ids":{"openalex":"https://openalex.org/W4297679012","doi":"https://doi.org/10.1145/3549737.3549808"},"language":"en","primary_location":{"id":"doi:10.1145/3549737.3549808","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3549737.3549808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Hellenic Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","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/A5040575826","display_name":"George A. Vouros","orcid":"https://orcid.org/0000-0001-5451-622X"},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"George Vouros","raw_affiliation_strings":["Dept. Digital Systems, AI Laboratory, University of Piraeus, Greece"],"affiliations":[{"raw_affiliation_string":"Dept. Digital Systems, AI Laboratory, University of Piraeus, Greece","institution_ids":["https://openalex.org/I154757721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040575826"],"corresponding_institution_ids":["https://openalex.org/I154757721"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12975022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.1257999986410141,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.1257999986410141,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1145000010728836,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8132699728012085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7276631593704224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4677598178386688},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.35574060678482056},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12519797682762146}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8132699728012085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276631593704224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4677598178386688},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.35574060678482056},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12519797682762146}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3549737.3549808","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3549737.3549808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Hellenic Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4220970489"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Interpretability,":[0],"explainability":[1,91,113,117],"and":[2,24,33,35,61,93,124,134,154],"transparency":[3],"are":[4,66],"key":[5],"issues":[6,26],"to":[7,21,29,72],"introducing":[8],"Artificial":[9],"Intelligence":[10],"closed\u2014box":[11],"methods":[12,68,123],"in":[13,43,46,52,75],"many":[14],"critical":[15,53],"domains:":[16],"This":[17,79],"is":[18,139],"important":[19,37,135],"due":[20],"ethical":[22],"concerns":[23],"trust":[25],"strongly":[27],"connected":[28],"reliability,":[30],"robustness,":[31],"auditability":[32],"fairness,":[34],"has":[36],"consequences":[38],"towards":[39,115],"keeping":[40],"the":[41,44,76,87,96,142,152],"human":[42],"loop":[45],"high":[47],"levels":[48],"of":[49,86,99,151],"automation,":[50],"especially":[51,62],"cases":[54],"for":[55],"decision":[56],"making.":[57],"Reinforcement":[58,148],"learning":[59,90,104],"methods,":[60],"their":[63],"deep":[64,88],"versions,":[65],"closed-box":[67],"that":[69],"support":[70],"agents":[71],"act":[73],"autonomously":[74],"real":[77],"world.":[78],"tutorial":[80,128,138],"will":[81,94,110,129],"provide":[82,111],"a":[83,100],"formal":[84],"specification":[85],"reinforcement":[89,103],"problems,":[92,118],"present":[95],"necessary":[97],"components":[98],"general":[101],"explainable":[102],"framework.":[105],"Based":[106],"on":[107,141,145],"this":[108],"framework":[109],"distinct":[112],"paradigms":[114],"solving":[116],"with":[119],"examples":[120],"from":[121],"state-of-the-art":[122],"real-world":[125],"cases.":[126],"The":[127,137],"conclude":[130],"identifying":[131],"open":[132],"questions":[133],"challenges.":[136],"based":[140],"survey":[143],"paper":[144],"\u201cExplainable":[146],"Deep":[147],"Learning\u201d":[149],"State":[150],"Art":[153],"Challenges\u201d":[155],"[1].":[156]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}