Actor-Critic--Type Learning Algorithms for Markov Decision Processes

Authors:
  • VKVijaymohan R. Konda
    Vijaymohan R. Konda
  • VBVivek S. Borkar
    Vivek S. Borkar

Abstract
Algorithms for learning the optimal policy of a Markov decision process (MDP) based on simulated transitions are formulated and analyzed. These are variants of the well-known "actor-critic" (or "adaptive critic") algorithm in the artificial intelligence literature. Distributed asynchronous implementations are considered. The analysis involves two time scale stochastic approximations.

This publication has 19 references indexed in Scilit: