{"id":"https://openalex.org/W4402365029","doi":"https://doi.org/10.14428/esann/2024.es2024-80","title":"Why long model-based rollouts are no reason for bad Q-value estimates","display_name":"Why long model-based rollouts are no reason for bad Q-value estimates","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402365029","doi":"https://doi.org/10.14428/esann/2024.es2024-80"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2024.es2024-80","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2024.es2024-80","pdf_url":"http://dx.doi.org/10.14428/esann/2024.es2024-80","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2024 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.14428/esann/2024.es2024-80","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/A5060543628","display_name":"Daniel Hein","orcid":"https://orcid.org/0000-0002-8375-1592"},"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/A5074808403","display_name":"Volker Tresp","orcid":"https://orcid.org/0000-0001-9428-3686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Volker Tresp","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":0.12347519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"485","last_page":"490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.5616000294685364,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.5616000294685364,"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/T10206","display_name":"Meta-analysis and systematic reviews","score":0.5432000160217285,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.5357000231742859,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5373700261116028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45807644724845886}],"concepts":[{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5373700261116028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45807644724845886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2024.es2024-80","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2024.es2024-80","pdf_url":"http://dx.doi.org/10.14428/esann/2024.es2024-80","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2024 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2024.es2024-80","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2024.es2024-80","pdf_url":"http://dx.doi.org/10.14428/esann/2024.es2024-80","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2024 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402365029.pdf","grobid_xml":"https://content.openalex.org/works/W4402365029.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0],"paper":[1,31],"explores":[2],"the":[3],"use":[4],"of":[5],"model-based":[6],"offline":[7],"reinforcement":[8,60],"learning":[9,61],"with":[10],"long":[11,36],"model":[12],"rollouts.While":[13],"some":[14],"literature":[15],"criticizes":[16],"this":[17],"approach":[18],"due":[19],"to":[20,33],"compounding":[21],"errors,":[22],"many":[23],"practitioners":[24],"have":[25],"found":[26],"success":[27],"in":[28,42],"real-world":[29],"applications.The":[30],"aims":[32],"demonstrate":[34],"that":[35],"rollouts":[37],"do":[38],"not":[39],"necessarily":[40],"result":[41],"exponentially":[43],"growing":[44],"errors":[45],"and":[46],"can":[47,57],"actually":[48],"produce":[49],"better":[50],"Q-value":[51],"estimates":[52],"than":[53],"model-free":[54],"methods.These":[55],"findings":[56],"potentially":[58],"enhance":[59],"techniques.":[62]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}