Reference
L. Buşoniu, D. Ernst, B. De Schutter, and R. Babuška,
"Consistency of fuzzy model-based reinforcement learning,"
Proceedings of the 2008 IEEE International Conference on Fuzzy
Systems (FUZZ-IEEE 2008), Hong Kong, pp. 518-524, June 2008.
Abstract
Reinforcement learning (RL) is a widely used paradigm for learning control.
Computing exact RL solutions is generally only possible when process states and
control actions take values in a small discrete set. In practice, approximate
algorithms are necessary. In this paper, we propose an approximate, model-based
Q-iteration algorithm that relies on a fuzzy partition of the state space, and
on a discretization of the action space. Using assumptions on the continuity of
the dynamics and of the reward function, we show that the resulting algorithm
is consistent, i.e., that the optimal solution is obtained asymptotically as
the approximation accuracy increases. An experimental study indicates that a
continuous reward function is also important for a predictable improvement in
performance as the approximation accuracy increases.
Downloads
BibTeX
@inproceedings{BusErn:08-005,
author = {Bu{\c{s}}oniu, Lucian and Ernst, Damien and De Schutter, Bart
and Babu{\v{s}}ka, Robert},
title = {Consistency of Fuzzy Model-Based Reinforcement Learning},
booktitle = {Proceedings of the 2008 IEEE International Conference on Fuzzy
Systems (FUZZ-IEEE 2008)},
address = {Hong Kong},
pages = {518--524},
month = jun,
year = {2008}
}