Generalised Entropy MDPs and Minimax Regret
Machine Learning
2014-12-11 v1 Machine Learning
Abstract
Bayesian methods suffer from the problem of how to specify prior beliefs. One interesting idea is to consider worst-case priors. This requires solving a stochastic zero-sum game. In this paper, we extend well-known results from bandit theory in order to discover minimax-Bayes policies and discuss when they are practical.
Cite
@article{arxiv.1412.3276,
title = {Generalised Entropy MDPs and Minimax Regret},
author = {Emmanouil G. Androulakis and Christos Dimitrakakis},
journal= {arXiv preprint arXiv:1412.3276},
year = {2014}
}
Comments
7 pages, NIPS workshop "From bad models to good policies"