Chapter

Emerging Intelligent Computing Technology and Applications. With Aspects of Artificial Intelligence

Volume 5755 of the series Lecture Notes in Computer Science pp 276-285

Using Control Theory for Analysis of Reinforcement Learning and Optimal Policy Properties in Grid-World Problems

  • S. Mostapha Kalami HerisAffiliated withControl Engineering Department, Faculty of Electrical Engineering, K. N. Toosi University of Technology
  • , Mohammad-Bagher Naghibi SistaniAffiliated withElectrical Engineering Department, Faculty of Engineering, Ferdowsi University of Mashhad
  • , Naser ParizAffiliated withElectrical Engineering Department, Faculty of Engineering, Ferdowsi University of Mashhad

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Markov Decision Process (MDP) has enormous applications in science, engineering, economics and management. Most of decision processes have Markov property and can be modeled as MDP. Reinforcement Learning (RL) is an approach to deal with MDPs. RL methods are based on Dynamic Programming (DP) algorithms, such as Policy Evaluation, Policy Iteration and Value Iteration. In this paper, policy evaluation algorithm is represented in the form of a discrete-time dynamical system. Hence, using Discrete-Time Control methods, behavior of agent and properties of various policies, can be analyzed. The general case of grid-world problems is addressed, and some important results are obtained for this type of problems as a theorem. For example, equivalent system of an optimal policy for a grid-world problem is dead-beat.

Keywords

Dynamic Programming Discrete-Time Control Systems Markov Decision Process Reinforcement Learning Stochastic Control