Summary: A Reinforcement Learning Method Based on Adaptive Simulated Annealing
Amir F. Atiya
Department of Computer Engineering
Cairo University
Giza, Egypt
amiratiya@link.net
Alexander G. Parlos
Department of Mechanical Engineering
Texas A&M University
College Station, Texas 77843
Email: a-parlos@tamu.edu
Telephone: +1 (979) 862­2060
Fax: +1 (979) 845­3081
Lester Ingber
Lester Ingber Research
ingber@ingber.com
Abstract-- Reinforcement learning is a hard problem and the
majority of the existing algorithms suffer from poor convergence
properties for difficult problems. In this paper we propose a new
reinforcement learning method, that utilizes the power of global

Source: Abu-Mostafa, Yaser S. - Department of Mechanical Engineering & Computer Science Department, California Institute of Technology

Collections: Computer Technologies and Information Sciences