{"id":"https://openalex.org/W4409479043","doi":"https://doi.org/10.14428/esann/2025.es2025-129","title":"Is Q-learning an Ill-posed Problem?","display_name":"Is Q-learning an Ill-posed Problem?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409479043","doi":"https://doi.org/10.14428/esann/2025.es2025-129"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2025.es2025-129","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-129","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-129","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2025.es2025-129","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107084033","display_name":"Philipp Wissmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philipp Wissmann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003471349","display_name":"Daniel Hein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Hein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035246650","display_name":"Steffen Udluft","orcid":"https://orcid.org/0000-0002-5767-2591"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steffen Udluft","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002518694","display_name":"Thomas A. Runkler","orcid":"https://orcid.org/0000-0002-5465-198X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Runkler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.06942654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"365","last_page":"370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10162","display_name":"Online and Blended Learning","score":0.478300005197525,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10162","display_name":"Online and Blended Learning","score":0.478300005197525,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/well-posed-problem","display_name":"Well-posed problem","score":0.8044971227645874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5468218326568604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2088475525379181},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.19691288471221924}],"concepts":[{"id":"https://openalex.org/C106214006","wikidata":"https://www.wikidata.org/wiki/Q1455898","display_name":"Well-posed problem","level":2,"score":0.8044971227645874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5468218326568604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2088475525379181},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.19691288471221924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2025.es2025-129","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-129","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-129","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2025.es2025-129","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-129","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-129","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409479043.pdf","grobid_xml":"https://content.openalex.org/works/W4409479043.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,34,56,81],"instability":[4,17],"of":[5,36,59,83],"Q-learning":[6,60,84],"in":[7,52],"continuous":[8],"environments,":[9],"a":[10,26,63,86],"challenge":[11],"frequently":[12],"encountered":[13],"by":[14,41],"practitioners.Traditionally,":[15],"this":[16],"is":[18],"attributed":[19],"to":[20,75],"bootstrapping":[21,37],"and":[22,38,73],"regression":[23],"model":[24,39],"errors.Using":[25],"representative":[27],"reinforcement":[28,90],"learning":[29,62,91],"benchmark,":[30],"we":[31],"systematically":[32],"examine":[33],"effects":[35],"inaccuracies":[40],"incrementally":[42],"eliminating":[43],"these":[44],"potential":[45],"error":[46],"sources.Our":[47],"findings":[48],"reveal":[49],"that":[50],"even":[51],"relatively":[53],"simple":[54],"benchmarks,":[55],"fundamental":[57],"task":[58],"-iteratively":[61],"Q-function":[64],"from":[65],"policy-specific":[66],"target":[67],"values":[68],"-can":[69],"be":[70],"inherently":[71],"ill-posed":[72],"prone":[74],"failure.These":[76],"insights":[77],"cast":[78],"doubt":[79],"on":[80],"reliability":[82],"as":[85],"universal":[87],"solution":[88],"for":[89],"problems.":[92]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
