DeepAI AI Chat
Log In Sign Up

On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning

by   Alain Durmus, et al.

This paper studies the exponential stability of random matrix products driven by a general (possibly unbounded) state space Markov chain. It is a cornerstone in the analysis of stochastic algorithms in machine learning (e.g. for parameter tracking in online learning or reinforcement learning). The existing results impose strong conditions such as uniform boundedness of the matrix-valued functions and uniform ergodicity of the Markov chains. Our main contribution is an exponential stability result for the p-th moment of random matrix product, provided that (i) the underlying Markov chain satisfies a super-Lyapunov drift condition, (ii) the growth of the matrix-valued functions is controlled by an appropriately defined function (related to the drift condition). Using this result, we give finite-time p-th moment bounds for constant and decreasing stepsize linear stochastic approximation schemes with Markovian noise on general state space. We illustrate these findings for linear value-function estimation in reinforcement learning. We provide finite-time p-th moment bound for various members of temporal difference (TD) family of algorithms.


page 1

page 2

page 3

page 4


The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning

The paper concerns convergence and asymptotic statistics for stochastic ...

A Multistep Lyapunov Approach for Finite-Time Analysis of Biased Stochastic Approximation

Motivated by the widespread use of temporal-difference (TD-) and Q-learn...

Finite-Time Analysis of Q-Learning with Linear Function Approximation

In this paper, we consider the model-free reinforcement learning problem...

Stable Reinforcement Learning with Unbounded State Space

We consider the problem of reinforcement learning (RL) with unbounded st...

Optimal Chernoff and Hoeffding Bounds for Finite Markov Chains

This paper develops an optimal Chernoff type bound for the probabilities...

Learning from non-irreducible Markov chains

Most of the existing literature on supervised learning problems focuses ...