The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation
Abstract
This paper gives specific divergence examples of value-iteration for several major Reinforcement Learning and Adaptive Dynamic Programming algorithms, when using a function approximator for the value function. These divergence examples differ from previous divergence examples in the literature, in that they are applicable for a greedy policy, i.e. in a "value iteration" scenario. Perhaps surprisingly, with a greedy policy, it is also possible to get divergence for the algorithms TD(1) and Sarsa(1). In addition to these divergences, we also achieve divergence for the Adaptive Dynamic Programming algorithms HDP, DHP and GDHP.
Cite
@article{arxiv.1107.4606,
title = {The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation},
author = {Michael Fairbank and Eduardo Alonso},
journal= {arXiv preprint arXiv:1107.4606},
year = {2012}
}
Comments
8 pages, 4 figures. In Proceedings of the IEEE International Joint Conference on Neural Networks, June 2012, Brisbane (IEEE IJCNN 2012), pp. 3070--3077