paper-with-me

홈 › Papers

Stability of Stochastic Approximations with `Controlled Markov' Noise and Temporal Difference Learning

2015-04-23 · Arunselvan Ramaswamy, Shalabh Bhatnagar

We are interested in understanding stability (almost sure boundedness) of stochastic approximation algorithms (SAs) driven by a controlled Markov' process. Analyzing this class of algorithms is important, since many reinforcement learning (RL) algorithms can be cast as SAs driven by a controlled Markov' process. In this paper, we present easily verifiable sufficient conditions for stability and convergence of SAs driven by a `controlled Markov' process. Many RL applications involve continuous state spaces. While our analysis readily ensures stability for such continuous state applications, traditional analyses do not. As compared to literature, our analysis presents a two-fold generalization (a) the Markov process may evolve in a continuous state space and (b) the process need not be ergodic under any given stationary policy. Temporal difference learning (TD) is an important policy evaluation method in reinforcement learning. The theory developed herein, is used to analyze generalized $TD(0)$, an important variant of TD. Our theory is also used to analyze a TD formulation of supervised learning for forecasting problems.

📄 PDF Abstract BibTeX arXiv:1504.06043

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Q-Learning for Stochastic Control under General Information Structures and Non-Markovian Environments

2023-10-31 · Ali Devran Kara, Serdar Yuksel

As a primary contribution, we present a convergence theorem for stochastic iterations, and in particular, Q-learning iterates, under a general, possibly non-Markovian, stochastic environment. Our conditions for convergen…

Q-LearningQuantization

Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning

2026-05-29 · Vagul Mahadevan, Claire Chen, Shuze Daniel Liu, Shangtong Zhang arxiv

This work studies the convergence of two-timescale stochastic approximations (SA), a class of iterative algorithms that update two sets of parameters in fast and slow timescales respectively. Notable examples of two-time…

Reinforcement Learning

Asymptotic and Finite Sample Analysis of Nonexpansive Stochastic Approximations with Markovian Noise

2024-09-29 · Ethan Blaser, Shangtong Zhang

Stochastic approximation is an important class of algorithms, and a large body of previous analysis focuses on stochastic approximations driven by contractive operators, which is not applicable in some important reinforc…

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

2021-01-30 · Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov 외

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 (…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Two Timescale Stochastic Approximation with Controlled Markov noise and Off-policy temporal difference learning

2015-03-31 · Prasenjit Karmakar, Shalabh Bhatnagar

We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive cont…