Training Reinforcement Neurocontrollers Using the Polytope Algorithm
Neural and Evolutionary Computing
2007-05-23 v1
Abstract
A new training algorithm is presented for delayed reinforcement learning problems that does not assume the existence of a critic model and employs the polytope optimization algorithm to adjust the weights of the action network so that a simple direct measure of the training performance is maximized. Experimental results from the application of the method to the pole balancing problem indicate improved training performance compared with critic-based and genetic reinforcement approaches.
Cite
@article{arxiv.cs/9812002,
title = {Training Reinforcement Neurocontrollers Using the Polytope Algorithm},
author = {A. Likas and I. E. Lagaris},
journal= {arXiv preprint arXiv:cs/9812002},
year = {2007}
}