{"id":"https://openalex.org/W4388329064","doi":"https://doi.org/10.48550/arxiv.2311.01104","title":"On the Convergence of Projected Policy Gradient for Any Constant Step Sizes","display_name":"On the Convergence of Projected Policy Gradient for Any Constant Step Sizes","publication_year":2023,"publication_date":"2023-11-02","ids":{"openalex":"https://openalex.org/W4388329064","doi":"https://doi.org/10.48550/arxiv.2311.01104"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.01104","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.01104","pdf_url":"https://arxiv.org/pdf/2311.01104","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.01104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015434452","display_name":"Jiacai Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Jiacai","raw_affiliation_strings":["School of Data Science , Fudan University , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science , Fudan University , Shanghai , China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112937484","display_name":"Wenye Li","orcid":"https://orcid.org/0000-0003-2767-8498","observed_orcids":["https://orcid.org/0000-0003-2767-8498","https://orcid.org/0009-0008-4616-9051"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Wenye","raw_affiliation_strings":["School of Data Science , Fudan University , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science , Fudan University , Shanghai , China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lin, Dachao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Dachao","raw_affiliation_strings":["Huawei Technologies Shanghai R&D Center , Shanghai China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Shanghai R&D Center , Shanghai China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei, Ke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei, Ke","raw_affiliation_strings":["School of Data Science , Fudan University , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science , Fudan University , Shanghai , China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393616","display_name":"Zhihua Zhang","orcid":"https://orcid.org/0000-0003-3165-5213","observed_orcids":["https://orcid.org/0000-0003-3165-5213","https://orcid.org/0000-0002-6449-4332","https://orcid.org/0000-0003-4391-9896","https://orcid.org/0000-0003-0122-2070","https://orcid.org/0000-0001-6111-4552","https://orcid.org/0000-0003-1969-6047"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zhihua","raw_affiliation_strings":["School of Mathematical Sciences , Peking University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences , Peking University , Beijing , China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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":0.0,"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/policy-optimization","display_name":"policy optimization","score":0.7509999871253967},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.7160000205039978},{"id":"https://openalex.org/keywords/constant-step-size","display_name":"constant step size","score":0.9470000267028809},{"id":"https://openalex.org/keywords/sublinear-convergence","display_name":"sublinear convergence","score":0.9300000071525574},{"id":"https://openalex.org/keywords/policy-iteration","display_name":"policy iteration","score":0.921999990940094},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.609000027179718}],"concepts":[{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.9383493661880493},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7039148807525635},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7038769721984863},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.6519285440444946},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.6406186819076538},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5760701894760132},{"id":"https://openalex.org/C62438384","wikidata":"https://www.wikidata.org/wiki/Q331350","display_name":"Simplex","level":2,"score":0.5257419347763062},{"id":"https://openalex.org/C5871375","wikidata":"https://www.wikidata.org/wiki/Q1780715","display_name":"Compact convergence","level":4,"score":0.4767804443836212},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.416983962059021},{"id":"https://openalex.org/C14928880","wikidata":"https://www.wikidata.org/wiki/Q1512559","display_name":"Normal convergence","level":4,"score":0.4160914123058319},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3367980420589447},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.23612123727798462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.20019462704658508},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.19136753678321838},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.17032626271247864},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.01104","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.01104","pdf_url":"https://arxiv.org/pdf/2311.01104","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.2311.01104","doi":"https://doi.org/10.48550/arxiv.2311.01104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.01104","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.01104","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.01104","pdf_url":"https://arxiv.org/pdf/2311.01104","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388329064.pdf","grobid_xml":"https://content.openalex.org/works/W4388329064.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1856231595","https://openalex.org/W2614208603","https://openalex.org/W2749807327","https://openalex.org/W2996037775","https://openalex.org/W4408158573"],"related_works":["https://openalex.org/W4394007427","https://openalex.org/W3044451384","https://openalex.org/W3157103014","https://openalex.org/W4221157223","https://openalex.org/W7171491360","https://openalex.org/W4387800773","https://openalex.org/W3109546547","https://openalex.org/W3206154452","https://openalex.org/W4225011832","https://openalex.org/W3011080757"],"abstract_inverted_index":{"Projected":[0],"policy":[1,7,17,59,106],"gradient":[2,39],"(PPG)":[3],"is":[4,122,163,167],"a":[5,85,114],"basic":[6],"optimization":[8],"method":[9],"in":[10,102],"reinforcement":[11],"learning.":[12],"Given":[13],"access":[14],"to":[15,52,56,94,125],"exact":[16],"evaluations,":[18],"previous":[19],"studies":[20],"have":[21],"established":[22],"the":[23,35,38,43,48,57,64,95,98,103,108,126,134,138,152],"sublinear":[24,86],"convergence":[25,65,87,155],"of":[26,42,66,97,105,117,128,143,156],"PPG":[27,54,67,83,118,144,157],"for":[28,69,88,113,158],"sufficiently":[29],"small":[30],"step":[31,49,71,91,161],"sizes":[32],"based":[33,145],"on":[34,146],"smoothness":[36],"and":[37,80],"domination":[40],"properties":[41],"value":[44],"function.":[45],"However,":[46],"as":[47],"size":[50,162],"goes":[51],"infinity,":[53],"reduces":[55],"classic":[58],"iteration":[60,154],"method,":[61],"which":[62,166],"suggests":[63],"even":[68],"large":[70],"sizes.":[72,92],"In":[73,150],"this":[74,78],"paper,":[75],"we":[76,132],"fill":[77],"gap":[79],"show":[81],"that":[82],"admits":[84],"any":[89,159],"constant":[90,160],"Due":[93],"existence":[96],"state-wise":[99,139],"visitation":[100],"measure":[101],"expression":[104],"gradient,":[107],"existing":[109],"optimization-based":[110],"analysis":[111],"framework":[112],"preconditioned":[115],"version":[116],"(i.e.,":[119],"projected":[120],"Q-ascent)":[121],"not":[123],"applicable,":[124],"best":[127],"our":[129],"knowledge.":[130],"Instead,":[131],"proceed":[133],"proof":[135],"by":[136],"computing":[137],"improvement":[140],"lower":[141],"bound":[142],"its":[147],"inherent":[148],"structure.":[149],"addition,":[151],"finite":[153],"further":[164],"established,":[165],"also":[168],"new.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-11-04T00:00:00"}