{"id":"https://openalex.org/W4305038384","doi":"https://doi.org/10.48550/arxiv.2210.05650","title":"Regret Bounds for Risk-Sensitive Reinforcement Learning","display_name":"Regret Bounds for Risk-Sensitive Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-11","ids":{"openalex":"https://openalex.org/W4305038384","doi":"https://doi.org/10.48550/arxiv.2210.05650"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.05650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.05650","pdf_url":"https://arxiv.org/pdf/2210.05650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.05650","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077991376","display_name":"O. Bastani","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bastani, O.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087023067","display_name":"Y. J. Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Y. J.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037836453","display_name":"Eric Tang Kui Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, E.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017984694","display_name":"W. Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, W.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077991376"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9972000122070312,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9972000122070312,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9817000031471252,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9775000214576721,"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/regret","display_name":"Regret","score":0.9432722330093384},{"id":"https://openalex.org/keywords/cvar","display_name":"CVAR","score":0.886240541934967},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.820969820022583},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5783874988555908},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4913085997104645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4779108464717865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46520787477493286},{"id":"https://openalex.org/keywords/risk-management","display_name":"Risk management","score":0.38280320167541504},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3430801331996918},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3409684896469116},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27570319175720215},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.25168687105178833},{"id":"https://openalex.org/keywords/expected-shortfall","display_name":"Expected shortfall","score":0.23797518014907837},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19993239641189575},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14732322096824646},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.1388286054134369},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09955358505249023},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.08961501717567444}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9432722330093384},{"id":"https://openalex.org/C2779922397","wikidata":"https://www.wikidata.org/wiki/Q5014755","display_name":"CVAR","level":4,"score":0.886240541934967},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.820969820022583},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5783874988555908},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4913085997104645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4779108464717865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46520787477493286},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.38280320167541504},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3430801331996918},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3409684896469116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27570319175720215},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.25168687105178833},{"id":"https://openalex.org/C5496284","wikidata":"https://www.wikidata.org/wiki/Q5420856","display_name":"Expected shortfall","level":3,"score":0.23797518014907837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19993239641189575},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14732322096824646},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.1388286054134369},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09955358505249023},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.08961501717567444}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.05650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.05650","pdf_url":"https://arxiv.org/pdf/2210.05650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.05650","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.05650","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.05650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.05650","pdf_url":"https://arxiv.org/pdf/2210.05650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2012697561","https://openalex.org/W3122289112","https://openalex.org/W3208862154","https://openalex.org/W2154756406","https://openalex.org/W2391449029","https://openalex.org/W315644267","https://openalex.org/W1904801170","https://openalex.org/W3177158450","https://openalex.org/W1925875298","https://openalex.org/W4292701710"],"abstract_inverted_index":{"In":[0],"safety-critical":[1],"applications":[2],"of":[3,41,57],"reinforcement":[4,35],"learning":[5,36],"such":[6],"as":[7,61,63],"healthcare":[8],"and":[9],"robotics,":[10],"it":[11],"is":[12,51],"often":[13],"desirable":[14],"to":[15],"optimize":[16],"risk-sensitive":[17,42],"objectives":[18,43],"that":[19],"account":[20],"for":[21,34],"tail":[22],"outcomes":[23],"rather":[24],"than":[25],"expected":[26],"reward.":[27],"We":[28],"prove":[29],"the":[30,45,58],"first":[31],"regret":[32],"bounds":[33],"under":[37],"a":[38,54,64],"general":[39],"class":[40],"including":[44],"popular":[46],"CVaR":[47,59],"objective.":[48],"Our":[49],"theory":[50],"based":[52],"on":[53],"novel":[55,65],"characterization":[56],"objective":[60],"well":[62],"optimistic":[66],"MDP":[67],"construction.":[68]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}