{"id":"https://openalex.org/W4400023655","doi":"https://doi.org/10.48550/arxiv.2406.16249","title":"An Optimal Tightness Bound for the Simulation Lemma","display_name":"An Optimal Tightness Bound for the Simulation Lemma","publication_year":2024,"publication_date":"2024-06-24","ids":{"openalex":"https://openalex.org/W4400023655","doi":"https://doi.org/10.48550/arxiv.2406.16249"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.16249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.16249","pdf_url":"https://arxiv.org/pdf/2406.16249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.16249","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016921301","display_name":"Sam Lobel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lobel, Sam","raw_affiliation_strings":["Department of Computer Science Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Brown University","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109839104","display_name":"Ronald Parr","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parr, Ronald","raw_affiliation_strings":["Department of Computer Science Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/model-misspecification","display_name":"model misspecification","score":0.8830000162124634},{"id":"https://openalex.org/keywords/discount-factor","display_name":"discount factor","score":0.7289999723434448},{"id":"https://openalex.org/keywords/hierarchical-abstraction","display_name":"hierarchical abstraction","score":0.9150000214576721},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.6828275918960571},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4393784999847412},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4181773066520691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3859325349330902},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.14454296231269836},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.04941031336784363},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.16249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.16249","pdf_url":"https://arxiv.org/pdf/2406.16249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.16249","doi":"https://doi.org/10.48550/arxiv.2406.16249","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.16249","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.16249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.16249","pdf_url":"https://arxiv.org/pdf/2406.16249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1006902961","display_name":null,"funder_award_id":"W911NF2210251","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G1370000603","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"2040433","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400023655.pdf","grobid_xml":"https://content.openalex.org/works/W4400023655.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W3006682748","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W1097487277","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596"],"abstract_inverted_index":{"We":[0,33,85],"present":[1],"a":[2,20,27,67,74,94],"bound":[3,75,96],"for":[4,43],"value-prediction":[5],"error":[6],"with":[7,79],"respect":[8,80],"to":[9,48,81],"model":[10],"misspecification":[11],"that":[12,35,76],"is":[13,19,77],"tight,":[14],"including":[15],"constant":[16],"factors.":[17],"This":[18],"direct":[21],"improvement":[22],"of":[23,52,65,69,90,101],"the":[24,49,98],"\"simulation":[25],"lemma,\"":[26],"foundational":[28],"result":[29],"in":[30,97],"reinforcement":[31],"learning.":[32],"demonstrate":[34,87],"existing":[36],"bounds":[37],"are":[38],"quite":[39],"loose,":[40],"becoming":[41],"vacuous":[42],"large":[44],"discount":[45],"factors,":[46],"due":[47],"suboptimal":[50],"treatment":[51],"compounding":[53],"probability":[54],"errors.":[55],"By":[56],"carefully":[57],"considering":[58],"this":[59,91],"quantity":[60],"on":[61],"its":[62],"own,":[63],"instead":[64],"as":[66],"subcomponent":[68],"value":[70],"error,":[71],"we":[72],"derive":[73],"sub-linear":[78],"transition":[82],"function":[83],"misspecification.":[84],"then":[86],"broader":[88],"applicability":[89],"technique,":[92],"improving":[93],"similar":[95],"related":[99],"subfield":[100],"hierarchical":[102],"abstraction.":[103]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}