{"id":"https://openalex.org/W7220454455","doi":"https://doi.org/10.48550/arxiv.2610.03642","title":"On the Convergence of Success Conditioning for Policy Optimization","display_name":"On the Convergence of Success Conditioning for Policy Optimization","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7220454455","doi":"https://doi.org/10.48550/arxiv.2610.03642"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.03642","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03642","pdf_url":"https://arxiv.org/pdf/2610.03642","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.03642","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130281355","display_name":"Matthew Brun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brun, Matthew","raw_affiliation_strings":["Operations Research Center , Massachusetts Institute of Technology , Cambridge , MA 02139 "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Operations Research Center , Massachusetts Institute of Technology , Cambridge , MA 02139 ","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004028534","display_name":"Xu Andy Sun","orcid":"https://orcid.org/0000-0003-3917-9418","observed_orcids":["https://orcid.org/0000-0003-3917-9418"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xu Andy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.9897000193595886,"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":0.9897000193595886,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.007799999788403511,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0015999999595806003,"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/policy-optimization","display_name":"policy optimization","score":0.9679999947547913},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.6819999814033508},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.8100000023841858},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9819999933242798},{"id":"https://openalex.org/keywords/optimal-policy","display_name":"optimal policy","score":0.5709999799728394},{"id":"https://openalex.org/keywords/stochastic-decision-making","display_name":"stochastic decision making","score":0.6290000081062317}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7565000057220459},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5817000269889832},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.579200029373169},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40459999442100525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40400001406669617},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.34610000252723694},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3393999934196472},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.28870001435279846},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2780388253","wikidata":"https://www.wikidata.org/wiki/Q5421508","display_name":"Exponent","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.03642","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03642","pdf_url":"https://arxiv.org/pdf/2610.03642","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.03642","doi":"https://doi.org/10.48550/arxiv.2610.03642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.03642","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.03642","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03642","pdf_url":"https://arxiv.org/pdf/2610.03642","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220454455.pdf","grobid_xml":"https://content.openalex.org/works/W7220454455.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W4401306886","https://openalex.org/W4416369109"],"related_works":["https://openalex.org/W7125817288","https://openalex.org/W7100587228","https://openalex.org/W4399758736","https://openalex.org/W7213516867","https://openalex.org/W3173515307","https://openalex.org/W7214990800","https://openalex.org/W7100319393","https://openalex.org/W2042680115","https://openalex.org/W2094964720","https://openalex.org/W3210035896"],"abstract_inverted_index":{"Success":[0,27],"conditioning":[1,28,54],"is":[2,29,105],"a":[3,14,61,103],"strategy":[4],"for":[5],"improving":[6],"decision-making":[7],"policies":[8],"in":[9,74],"stochastic":[10],"environments;":[11],"it":[12],"updates":[13],"policy":[15,59,104],"by":[16],"increasing":[17],"the":[18,92],"probability":[19],"of":[20,64],"taking":[21],"actions":[22],"that":[23,52],"yield":[24],"successful":[25],"outcomes.":[26],"common":[30,76],"to":[31,56,87],"many":[32],"reinforcement":[33],"learning":[34],"applications,":[35],"yet":[36],"its":[37],"limiting":[38],"behavior":[39],"and":[40],"convergence":[41,72,83],"rates":[42,73],"are":[43],"not":[44],"well":[45],"understood.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,81],"demonstrate":[51],"success":[53],"converges":[55],"an":[57,88],"optimal":[58],"on":[60,96],"broad":[62],"class":[63],"Markov":[65],"decision":[66],"processes":[67],"(MDPs).":[68],"We":[69],"also":[70],"derive":[71],"some":[75],"settings.":[77],"For":[78,99],"discounted":[79],"MDPs,":[80,101],"prove":[82],"within":[84,107],"$\\mathcal{O}(1/\\varepsilon^p)$":[85],"iterations":[86],"$\\varepsilon$-optimal":[89],"policy,":[90],"where":[91],"exponent":[93],"$p$":[94],"depends":[95],"problem":[97],"data.":[98],"single-period":[100],"such":[102],"obtained":[106],"$\\mathcal{O}(\\log(1/\\varepsilon))$":[108],"iterations.":[109]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-06T00:00:00"}