{"id":"https://openalex.org/W4414359755","doi":"https://doi.org/10.24963/ijcai.2025/665","title":"A Case for Validation Buffer in Pessimistic Actor-Critic","display_name":"A Case for Validation Buffer in Pessimistic Actor-Critic","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359755","doi":"https://doi.org/10.24963/ijcai.2025/665"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/665","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint 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/A5069074931","display_name":"Micha\u0142 Nauman","orcid":"https://orcid.org/0009-0001-3241-6663"},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Micha\u0142 Nauman","raw_affiliation_strings":["University of Warsaw"],"affiliations":[{"raw_affiliation_string":"University of Warsaw","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036002931","display_name":"Mateusz Ostaszewski","orcid":"https://orcid.org/0000-0001-7915-6662"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Mateusz Ostaszewski","raw_affiliation_strings":["Warsaw University of Technology"],"affiliations":[{"raw_affiliation_string":"Warsaw University of Technology","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037989463","display_name":"Marek Cygan","orcid":"https://orcid.org/0000-0003-2472-2975"},"institutions":[{"id":"https://openalex.org/I4210127782","display_name":"Botswana Geoscience Institute","ror":"https://ror.org/038fqq280","country_code":"BW","type":"other","lineage":["https://openalex.org/I4210127782"]},{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["BW","PL"],"is_corresponding":false,"raw_author_name":"Marek Cygan","raw_affiliation_strings":["Nomagic","University of Warsaw"],"affiliations":[{"raw_affiliation_string":"Nomagic","institution_ids":["https://openalex.org/I4210127782"]},{"raw_affiliation_string":"University of Warsaw","institution_ids":["https://openalex.org/I4654613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069074931"],"corresponding_institution_ids":["https://openalex.org/I4654613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26669323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5976","last_page":"5984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14394","display_name":"Cognitive Science and Education Research","score":0.057999998331069946,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T14394","display_name":"Cognitive Science and Education Research","score":0.057999998331069946,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12469","display_name":"Chaos, Complexity, and Education","score":0.04859999939799309,"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/pessimism","display_name":"Pessimism","score":0.9078999757766724},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6000999808311462},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5654000043869019},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.44589999318122864},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.39489999413490295},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.3521000146865845},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3395000100135803}],"concepts":[{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.9078999757766724},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6000999808311462},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5654000043869019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5166000127792358},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3950999975204468},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3804999887943268},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/665","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,61],"investigate":[4,100],"the":[5,22,38,48,52,76,81,85,90,94,101],"issue":[6],"of":[7,37,78,93,107],"error":[8,25,92],"accumulation":[9],"in":[10,115],"critic":[11,23,54,95],"networks":[12],"updated":[13],"via":[14,29],"pessimistic":[15,53],"temporal":[16],"difference":[17],"objectives.":[18],"We":[19,41,99],"show":[20],"that":[21,36,89],"approximation":[24,91],"can":[26],"be":[27],"approximated":[28],"a":[30,70,105],"recursive":[31,44],"fixed-point":[32],"model":[33],"similar":[34],"to":[35,46,74],"Bellman":[39],"value.":[40],"use":[42],"such":[43,88],"definition":[45],"retrieve":[47],"conditions":[49],"under":[50],"which":[51],"is":[55,97],"unbiased.":[56],"Building":[57],"on":[58,104],"these":[59],"insights,":[60],"propose":[62],"Validation":[63],"Pessimism":[64],"Learning":[65],"(VPL)":[66],"algorithm.":[67],"VPL":[68],"uses":[69],"small":[71],"validation":[72],"buffer":[73],"adjust":[75],"levels":[77],"pessimism":[79,86],"throughout":[80],"agent":[82],"training,":[83],"with":[84],"set":[87],"targets":[96],"minimized.":[98],"proposed":[102],"approach":[103],"variety":[106],"locomotion":[108],"and":[109,112,118],"manipulation":[110],"tasks":[111],"report":[113],"improvements":[114],"sample":[116],"efficiency":[117],"performance.":[119]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}