Toward Z-number Valued Reinforcement Learning Problem

Jabbarova K., Huseynov O., Jabbarova A.

12th World Conference on Intelligent Systems for Industrial Automation, WCIS 2022, Tashkent, Uzbekistan, 25 - 26 November 2022, vol.718 LNNS, pp.352-360, (Full Text)

  • Publication Type: Conference Paper / Full Text
  • Volume: 718 LNNS
  • Doi Number: 10.1007/978-3-031-51521-7_44
  • City: Tashkent
  • Country: Uzbekistan
  • Page Numbers: pp.352-360
  • Keywords: fuzzy number, reinforcement learning, uncertainty, Z-number
  • Open Archive Collection: Conference Paper, Article
  • Azerbaijan State University of Economics (UNEC) Affiliated: Yes

Abstract

Real-world decision-making problems are characterized by a fusion of fuzzy and probabilistic uncertainties. In view of this, Zadeh introduced the concept of Z-number to describe imprecision and partial reliability of decision relevant information. In this paper we proposed an approach to solving Q-learning problem where rewards and constraints over actions are described by using Z-numbers. A typical decision problem is used to illustrate the approach.