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.
Meanwhile, since(1−λ)e x −1>−1>−e x, it can be guaranteed that [(1−λ)e x −1] hp ((1−λ)e x −x) 2 + 4(ex −1) 2 −((1−λ)e x −x) i + 4(ex −1)e x >−e x[2(ex −1)] + 4(e x −1)e x >0
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.