Improved high-probability bounds for the temporal difference learning algorithm via exponential stability

Sergey Samsonov^a, Daniil Tiapkin^bc, Alexey Naumov^ad, Eric Moulines<sup>b

a</sup> HSE University, Moscow, Russia
^b Centre de Mathématiques Appliquées – CNRS – École polytechnique – Institut Polytechnique de Paris, France
^c Université Paris-Saclay, CNRS, Laboratoire de mathématiques d'Orsay, France
^d Steklov Mathematical Institute of Russian Academy of Sciences, Moscow, Russia

Язык публикации: английский