{"id":"https://openalex.org/W7154622630","doi":"https://doi.org/10.14428/esann/2026.es2026-253","title":"Point-wise Q-value maximization for converging Q-learning in continuous state-spaces","display_name":"Point-wise Q-value maximization for converging Q-learning in continuous state-spaces","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154622630","doi":"https://doi.org/10.14428/esann/2026.es2026-253"},"language":null,"primary_location":{"id":"doi:10.14428/esann/2026.es2026-253","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2026.es2026-253","pdf_url":"https://doi.org/10.14428/esann/2026.es2026-253","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2026 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/2026.es2026-253","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133818898","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/A5133760636","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/A5133795756","display_name":"Thomas Runkler","orcid":null},"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":0.56534234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"595","last_page":"600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2639999985694885,"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":0.2639999985694885,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.11949999630451202,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.09549999982118607,"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/maximization","display_name":"Maximization","score":0.3928999900817871},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.302700012922287},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.29319998621940613},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.2896000146865845},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.2761000096797943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4422999918460846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4142000079154968},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2026.es2026-253","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2026.es2026-253","pdf_url":"https://doi.org/10.14428/esann/2026.es2026-253","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2026 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2026.es2026-253","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2026.es2026-253","pdf_url":"https://doi.org/10.14428/esann/2026.es2026-253","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2026 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7154622630.pdf","grobid_xml":"https://content.openalex.org/works/W7154622630.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,30,54,67],"novel":[4],"Q-learning":[5,72],"framework":[6],"to":[7,59],"address":[8],"instabilities":[9],"in":[10,73],"offline":[11],"reinforcement":[12],"learning":[13],"with":[14,38],"continuous":[15],"state":[16],"spaces.We":[17],"identify":[18],"the":[19,35,78],"recurring":[20],"collapse":[21],"of":[22,80],"Q-value":[23],"targets":[24,37],"as":[25],"core":[26],"challenge":[27],"and":[28,47,76],"propose":[29],"stabilization":[31],"technique":[32],"that":[33,53],"replaces":[34],"iteration-wise":[36],"their":[39],"point-wise":[40],"maximum":[41],"across":[42],"iterations.This":[43],"approach":[44],"enforces":[45],"convergence":[46],"fully":[48],"mitigates":[49],"recursive":[50],"errors.We":[51],"show":[52],"performance":[55,61],"metric":[56],"linking":[57],"Q-values":[58],"policy":[60],"is":[62],"directly":[63],"available.Our":[64],"findings":[65],"represent":[66],"first":[68],"step":[69],"toward":[70],"stabilizing":[71],"challenging":[74],"settings":[75],"highlight":[77],"potential":[79],"model-based":[81],"approaches.":[82]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-17T00:00:00"}