ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1504.06043
45
21
v1v2 (latest)

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

23 April 2015
Arunselvan Ramaswamy
S. Bhatnagar
ArXiv (abs)PDFHTML
Abstract

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)TD(0)TD(0), an important variant of TD. Our theory is also used to analyze a TD formulation of supervised learning for forecasting problems.

View on arXiv
Comments on this paper