Math 2.0

Resources / preprint

An analysis of Mirror-Descent Soft Actor-Critic MVR35ZJPCC

URIm2://res/MVR35ZJPCC
Kindpreprint
CreatorsDenis Zorba, Michal Valko
Date2026-09-28
Subjectsarxiv cs.LG, arxiv math.OC, arxiv stat.ML
Scopeborder

Expressions

e1: version, preprint

Date2026-09-28
IdsarXiv 2609.35466

Items in this resource

The mentions of the inventory that name this resource. Each name links to the card of its inventory row.

ItemKindWhereSource
Three point lemma/Bregman proximal inequalitystatementlemma 6arxiv
53S8FAF6K5statementlemma 3arxiv
Gaussian approximation errordefinitiondefinition 3arxiv
A94FRCCXC2statementtheorem 2arxiv
Actor trackingstatementlemma 2arxiv
Push-forward measuredefinitiondefinition 1arxiv
DYKBEH7Y7Fdefinitiondefinition 4arxiv
Squashed Gaussian Policiesdefinitiondefinition 2arxiv
Entropy of a squashed Gaussian policystatementlemma 5arxiv
F1E076PHS0statementcorollary 1arxiv
HYT4GV9B8Xdefinitiondefinition 5arxiv
JMRXR1CNHQstatementtheorem 5arxiv
QFC4ZM5Z0Astatementlemma 9arxiv
RP9G6G8K0Rstatementtheorem 1arxiv
TW311DAT7Xstatementtheorem 3arxiv
W36K3CSD1Hstatementlemma 7arxiv
Performance differencestatementlemma 4arxiv
Uniform boundedness of the actor gradientstatementlemma 8arxiv
Dynamic Programming Principlestatementtheorem 4arxiv
ZH6TVCT5P0statementlemma 1arxiv

Catalogue records