Derives novel high-dimensional concentration inequalities for vector-valued Markov chain martingales and applies them to TD learning for consistency guarantees matching asymptotic variance up to logs and O(T^{-1/4} log T) Gaussian approximation rate.
tmixηt−tmix(2∥θ⋆∥2 + 1) + 2ηt−tmix t−2X i=t−tmix E∥∆i∥2 # =−η t−tmix(2∥θ⋆∥2 + 1)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Uncertainty quantification for Markov chain induced martingales with application to temporal difference learning
Derives novel high-dimensional concentration inequalities for vector-valued Markov chain martingales and applies them to TD learning for consistency guarantees matching asymptotic variance up to logs and O(T^{-1/4} log T) Gaussian approximation rate.