{"id":"https://openalex.org/W4415209251","doi":"https://doi.org/10.1007/978-3-032-08324-1_11","title":"Explain to\u00a0Gain: Introspective Reinforcement Learning for\u00a0Enhanced Performance","display_name":"Explain to\u00a0Gain: Introspective Reinforcement Learning for\u00a0Enhanced Performance","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415209251","doi":"https://doi.org/10.1007/978-3-032-08324-1_11"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-08324-1_11","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-08324-1_11","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-08324-1_11.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":"book-chapter","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_11.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086150518","display_name":"Santiago Quintana-Amate","orcid":null},"institutions":[{"id":"https://openalex.org/I94706221","display_name":"Airbus (United Kingdom)","ror":"https://ror.org/02hbhxa68","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210121748","https://openalex.org/I94706221"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Santiago Quintana-Amate","raw_affiliation_strings":["Airbus AI Research, Filton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Airbus AI Research, Filton, UK","institution_ids":["https://openalex.org/I94706221"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Delaney Stevens","orcid":null},"institutions":[{"id":"https://openalex.org/I94706221","display_name":"Airbus (United Kingdom)","ror":"https://ror.org/02hbhxa68","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210121748","https://openalex.org/I94706221"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Delaney Stevens","raw_affiliation_strings":["Airbus AI Research, Filton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Airbus AI Research, Filton, UK","institution_ids":["https://openalex.org/I94706221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120008973","display_name":"Varniethan Ketheeswaran","orcid":null},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]},{"id":"https://openalex.org/I94706221","display_name":"Airbus (United Kingdom)","ror":"https://ror.org/02hbhxa68","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210121748","https://openalex.org/I94706221"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Varniethan Ketheeswaran","raw_affiliation_strings":["Airbus AI Research, Filton, UK","University of Bath, Bath, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Airbus AI Research, Filton, UK","institution_ids":["https://openalex.org/I94706221"]},{"raw_affiliation_string":"University of Bath, Bath, UK","institution_ids":["https://openalex.org/I51601045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120008974","display_name":"Patrick Capaldo","orcid":null},"institutions":[{"id":"https://openalex.org/I94706221","display_name":"Airbus (United Kingdom)","ror":"https://ror.org/02hbhxa68","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210121748","https://openalex.org/I94706221"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick Capaldo","raw_affiliation_strings":["Airbus AI Research, Filton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Airbus AI Research, Filton, UK","institution_ids":["https://openalex.org/I94706221"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dylan Sheldon","orcid":null},"institutions":[{"id":"https://openalex.org/I114203471","display_name":"University of Gloucestershire","ror":"https://ror.org/00wygct11","country_code":"GB","type":"education","lineage":["https://openalex.org/I114203471"]},{"id":"https://openalex.org/I94706221","display_name":"Airbus (United Kingdom)","ror":"https://ror.org/02hbhxa68","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210121748","https://openalex.org/I94706221"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dylan Sheldon","raw_affiliation_strings":["Airbus AI Research, Filton, UK","University of Gloucestershire, Cheltenham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Airbus AI Research, Filton, UK","institution_ids":["https://openalex.org/I94706221"]},{"raw_affiliation_string":"University of Gloucestershire, Cheltenham, UK","institution_ids":["https://openalex.org/I114203471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065290010","display_name":"Mark A. Hall","orcid":"https://orcid.org/0000-0001-6277-144X"},"institutions":[{"id":"https://openalex.org/I94706221","display_name":"Airbus (United Kingdom)","ror":"https://ror.org/02hbhxa68","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210121748","https://openalex.org/I94706221"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Hall","raw_affiliation_strings":["Airbus AI Research, Filton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Airbus AI Research, Filton, UK","institution_ids":["https://openalex.org/I94706221"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5086150518"],"corresponding_institution_ids":["https://openalex.org/I94706221"],"apc_list":null,"apc_paid":null,"fwci":3.3248,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93199628,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9851999878883362,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9526000022888184},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8615000247955322},{"id":"https://openalex.org/keywords/introspection","display_name":"Introspection","score":0.6215999722480774},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3718000054359436}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9526000022888184},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8615000247955322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746399998664856},{"id":"https://openalex.org/C129671850","wikidata":"https://www.wikidata.org/wiki/Q210501","display_name":"Introspection","level":2,"score":0.6215999722480774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034999847412109},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3808000087738037},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.336899995803833},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.23829999566078186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-08324-1_11","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-08324-1_11","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-08324-1_11.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"}],"best_oa_location":{"id":"doi:10.1007/978-3-032-08324-1_11","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-08324-1_11","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-08324-1_11.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/W4415209251.pdf","grobid_xml":"https://content.openalex.org/works/W4415209251.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2084312543","https://openalex.org/W2740302738","https://openalex.org/W2902907165","https://openalex.org/W2952561542","https://openalex.org/W2982316857","https://openalex.org/W2996001543","https://openalex.org/W2998004401","https://openalex.org/W3037614835","https://openalex.org/W3082925502","https://openalex.org/W3116073702","https://openalex.org/W3124922852","https://openalex.org/W3196440773","https://openalex.org/W3199500857","https://openalex.org/W4285819208","https://openalex.org/W4366783122","https://openalex.org/W4386193536","https://openalex.org/W4388012893","https://openalex.org/W4391399751","https://openalex.org/W4392662712","https://openalex.org/W4396506409","https://openalex.org/W4405209173"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1,77,139],"article":[2],"presents":[3],"a":[4],"new":[5],"method":[6],"for":[7,39,156],"leveraging":[8],"explainable":[9],"reinforcement":[10,19],"learning":[11,20],"(XRL)":[12],"knowledge":[13],"to":[14,44,119],"enhance":[15],"the":[16,70,128,131,154],"performance":[17,151],"of":[18,73,82,127],"(RL)":[21],"agents.":[22],"Although":[23],"current":[24],"XRL":[25,66,90,116,143],"approaches":[26],"are":[27],"mainly":[28],"focused":[29],"on":[30,86],"improving":[31],"interpretability":[32,148],"and":[33,46,103,109,136,159],"user":[34],"trust":[35],"by":[36,64,146],"providing":[37],"explanations":[38],"agent":[40,123],"actions,":[41],"their":[42],"ability":[43],"guide":[45],"optimise":[47],"RL":[48,75,161],"agent\u2019s":[49],"training":[50,71],"is":[51,95],"under-explored.":[52],"To":[53],"address":[54],"this":[55],"gap,":[56],"we":[57,112],"extend":[58],"an":[59],"existing":[60],"introspective":[61],"analysis":[62,126],"framework":[63],"integrating":[65],"metrics":[67],"directly":[68],"into":[69],"pipelines":[72],"model-free":[74],"algorithms.":[76],"integration":[78],"allows":[79],"dynamic":[80],"adjustments":[81],"algorithm-specific":[83],"parameters":[84],"based":[85],"real-time":[87],"feedback":[88],"from":[89],"metrics.":[91],"The":[92,125],"proposed":[93],"methodology":[94],"validated":[96],"across":[97],"diverse":[98],"OpenAI":[99],"Gym":[100],"environments":[101],"(CartPole":[102],"Taxi).":[104],"By":[105],"evaluating":[106],"both":[107],"on-policy":[108],"off-policy":[110],"approaches,":[111],"demonstrate":[113],"that":[114],"incorporating":[115],"insights":[117],"leads":[118],"significant":[120],"improvements":[121],"in":[122,142,163],"performance.":[124],"results":[129],"highlights":[130],"benefits":[132],"regarding":[133],"enhanced":[134],"explainability":[135],"optimised":[137],"decision-making.":[138],"work":[140],"contributes":[141],"research":[144],"area":[145],"aligning":[147],"with":[149],"actionable":[150],"gains,":[152],"paving":[153],"way":[155],"more":[157],"reliable":[158],"transparent":[160],"systems":[162],"complex,":[164],"real-world":[165],"applications.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-16T00:00:00"}
