{"id":"https://openalex.org/W3041828093","doi":"https://doi.org/10.24963/ijcai.2020/706","title":"On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)","display_name":"On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3041828093","doi":"https://doi.org/10.24963/ijcai.2020/706","mag":"3041828093"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/706","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/706","pdf_url":"https://www.ijcai.org/proceedings/2020/0706.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0706.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015166903","display_name":"Vincent Fran\u00e7ois-Lavet","orcid":"https://orcid.org/0000-0002-8593-9740"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vincent Francois-Lavet","raw_affiliation_strings":["McGill University","Mila"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"Mila","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023766963","display_name":"Guillaume Rabusseau","orcid":"https://orcid.org/0000-0001-8090-2810"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Guillaume Rabusseau","raw_affiliation_strings":["Mila","Universit\u00e9 de Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila","institution_ids":[]},{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joelle Pineau","raw_affiliation_strings":["McGill University","Mila"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"Mila","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077011518","display_name":"Damien Ernst","orcid":"https://orcid.org/0000-0002-3035-8260"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Damien Ernst","raw_affiliation_strings":["Universit\u00e9 de Li\u00e8ge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Li\u00e8ge","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031489638","display_name":"Rapha\u00ebl Fonteneau","orcid":"https://orcid.org/0000-0002-7850-1548"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Raphael Fonteneau","raw_affiliation_strings":["Universit\u00e9 de Li\u00e8ge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Li\u00e8ge","institution_ids":["https://openalex.org/I157674565"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.115,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34619943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5055","last_page":"5059"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9743536710739136},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.9453480839729309},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8341082334518433},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6748639345169067},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6074546575546265},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5486664175987244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5305877923965454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44145336747169495},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4191567897796631},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38756832480430603},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.25551414489746094},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24370485544204712},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19963952898979187}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9743536710739136},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9453480839729309},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8341082334518433},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6748639345169067},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6074546575546265},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5486664175987244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5305877923965454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44145336747169495},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4191567897796631},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38756832480430603},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.25551414489746094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24370485544204712},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19963952898979187},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/706","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/706","pdf_url":"https://www.ijcai.org/proceedings/2020/0706.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/706","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/706","pdf_url":"https://www.ijcai.org/proceedings/2020/0706.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318621","display_name":"Waalse Gewest","ror":null},{"id":"https://openalex.org/F4320330273","display_name":"Institut de Valorisation des Donn\u00e9es","ror":null},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3041828093.pdf","grobid_xml":"https://content.openalex.org/works/W3041828093.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W1532688806","https://openalex.org/W1540337045","https://openalex.org/W1568770747","https://openalex.org/W1583380718","https://openalex.org/W1591992921","https://openalex.org/W1844343792","https://openalex.org/W1893127244","https://openalex.org/W2044375425","https://openalex.org/W2099873296","https://openalex.org/W2158282517","https://openalex.org/W2168359464","https://openalex.org/W2460675832","https://openalex.org/W2468354762","https://openalex.org/W2964241534","https://openalex.org/W3004707083","https://openalex.org/W3123298421","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W1971989957","https://openalex.org/W2922073769"],"abstract_inverted_index":{"When":[0],"an":[1,12,28,59],"agent":[2],"has":[3],"limited":[4,45],"information":[5],"on":[6],"its":[7],"environment,":[8],"the":[9,19,48,62,82,87],"suboptimality":[10,42],"of":[11,21,50,61,89],"RL":[13],"algorithm":[14],"can":[15],"be":[16],"decomposed":[17],"into":[18],"sum":[20],"two":[22,66],"terms:":[23],"a":[24,36,77],"term":[25,37],"related":[26],"to":[27,39,44],"asymptotic":[29,83],"bias":[30,84],"(suboptimality":[31],"with":[32,53],"unlimited":[33],"data)":[34],"and":[35],"due":[38,43],"overfitting":[40],"(additional":[41],"data).":[46],"In":[47,69],"context":[49],"reinforcement":[51],"learning":[52],"partial":[54],"observability,":[55],"this":[56],"paper":[57],"provides":[58],"analysis":[60,73],"tradeoff":[63],"between":[64],"these":[65],"error":[67],"sources.":[68],"particular,":[70],"our":[71],"theoretical":[72],"formally":[74],"characterizes":[75],"how":[76],"smaller":[78],"state":[79],"representation":[80],"increases":[81],"while":[85],"decreasing":[86],"risk":[88],"overfitting.":[90]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}