{"id":"https://openalex.org/W7214726774","doi":"https://doi.org/10.48550/arxiv.2609.35466","title":"An analysis of Mirror-Descent Soft Actor-Critic","display_name":"An analysis of Mirror-Descent Soft Actor-Critic","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214726774","doi":"https://doi.org/10.48550/arxiv.2609.35466"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.35466","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35466","pdf_url":"https://arxiv.org/pdf/2609.35466","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/2609.35466","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125719059","display_name":"Denis Zorba","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zorba, Denis","raw_affiliation_strings":["School of Mathematics , University of Edinburgh , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics , University of Edinburgh , United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106038276","display_name":"Michal Valko","orcid":"https://orcid.org/0009-0009-2673-0144","observed_orcids":["https://orcid.org/0009-0009-2673-0144"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Valko, Michal","raw_affiliation_strings":["INRIA , Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA , Paris , France","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"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":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":0.0005000000237487257,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/soft-actor-critic","display_name":"soft actor-critic","score":0.8659999966621399},{"id":"https://openalex.org/keywords/finite-time-convergence","display_name":"finite-time convergence","score":0.6359999775886536},{"id":"https://openalex.org/keywords/continuous-action-spaces","display_name":"continuous action spaces","score":0.7139999866485596}],"concepts":[{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.7127000093460083},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5902000069618225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5386000275611877},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.41280001401901245},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.39890000224113464},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3682999908924103},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3650999963283539},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.32199999690055847},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C111458787","wikidata":"https://www.wikidata.org/wiki/Q215405","display_name":"Legendre polynomials","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.35466","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35466","pdf_url":"https://arxiv.org/pdf/2609.35466","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.2609.35466","doi":"https://doi.org/10.48550/arxiv.2609.35466","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.35466","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:2609.35466","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35466","pdf_url":"https://arxiv.org/pdf/2609.35466","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/W7214726774.pdf","grobid_xml":"https://content.openalex.org/works/W7214726774.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2047364871","https://openalex.org/W2100677568","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2296883750","https://openalex.org/W2502318419","https://openalex.org/W2736601468","https://openalex.org/W2904246096","https://openalex.org/W3026615607","https://openalex.org/W3127686539","https://openalex.org/W3217314940","https://openalex.org/W4245755263","https://openalex.org/W4317897806","https://openalex.org/W4381739798","https://openalex.org/W4401142486","https://openalex.org/W4413213072","https://openalex.org/W7162406948","https://openalex.org/W7196953070","https://openalex.org/W7202204005"],"related_works":["https://openalex.org/W7128724396","https://openalex.org/W4407245006","https://openalex.org/W4382763229","https://openalex.org/W4226165675","https://openalex.org/W4323076369","https://openalex.org/W3026615607","https://openalex.org/W7167891200","https://openalex.org/W2981750972","https://openalex.org/W4414592201","https://openalex.org/W7214658707"],"abstract_inverted_index":{"Soft":[0],"Actor-Critic":[1],"(SAC)":[2],"is":[3],"widely":[4],"used":[5],"for":[6,55],"entropy-regularised":[7],"reinforcement":[8],"learning":[9],"with":[10,46],"continuous":[11],"action":[12],"spaces,":[13],"and":[14,43,59,78,89,104],"practical":[15],"implementations":[16],"perform":[17],"only":[18],"a":[19,115],"few":[20],"actor":[21,63,88,106],"steps":[22],"towards":[23],"an":[24,80],"evolving":[25],"target.":[26,50],"In":[27],"this":[28],"work,":[29],"we":[30],"prove":[31],"convergence":[32,84],"guarantees":[33],"when":[34],"the":[35,47,56,62,67,70,74,94,101,110],"target":[36,102],"policy":[37,40],"arises":[38],"from":[39],"mirror":[41],"descent":[42],"compare":[44],"it":[45],"classical":[48],"Gibbs":[49,112],"We":[51],"derive":[52],"sufficient":[53],"conditions":[54],"strong":[57],"convexity":[58],"smoothness":[60],"of":[61,69],"objective,":[64],"characterised":[65],"by":[66],"curvature":[68],"$Q$-function":[71],"estimate":[72],"through":[73],"Legendre":[75],"differential":[76],"operator,":[77],"establish":[79],"$\\mathcal{O}\\!\\left(N^{-\\frac{1}{5}}\\right)$":[81],"best-iterate":[82],"finite-time":[83],"rate":[85],"up":[86],"to":[87],"critic":[90],"approximation":[91],"errors.":[92],"Moreover,":[93],"mirror-descent":[95],"step":[96],"size":[97],"$\u03bb$":[98],"directly":[99],"controls":[100],"drift":[103],"hence":[105],"tracking":[107,117],"error,":[108],"whereas":[109],"analogous":[111],"bound":[113],"contains":[114],"non-vanishing":[116],"term.":[118]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}