Quantile Reinforcement Learning
Machine Learning
2016-11-04 v1 Artificial Intelligence
Abstract
In reinforcement learning, the standard criterion to evaluate policies in a state is the expectation of (discounted) sum of rewards. However, this criterion may not always be suitable, we consider an alternative criterion based on the notion of quantiles. In the case of episodic reinforcement learning problems, we propose an algorithm based on stochastic approximation with two timescales. We evaluate our proposition on a simple model of the TV show, Who wants to be a millionaire.
Cite
@article{arxiv.1611.00862,
title = {Quantile Reinforcement Learning},
author = {Hugo Gilbert and Paul Weng},
journal= {arXiv preprint arXiv:1611.00862},
year = {2016}
}
Comments
AWRL 2016