On using discretized Cohen-Grossberg node dynamics for model-free actor-critic neural learning in non-Markovian domains

Abstract

We describe how multi-stage non-Markovian decision problems can be solved using actor-critic reinforcement learning by assuming that a discrete version of CohenGrossberg node dynamics describes the node-activation computations of a neural network (NN). Our NN (i.e., agent) is capable of rendering the process Markovian implicitly and automatically in a… (More)
DOI: 10.1109/CIRA.2003.1222053

2 Figures and Tables

Topics

  • Presentations referencing similar topics