Generalised Entropy MDPs and Minimax Regret

Autor:	Androulakis, Emmanouil G., Dimitrakakis, Christos
Rok vydání:	2014
Předmět:	Computer Science - Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: 7 pages, NIPS workshop "From bad models to good policies"
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1412.3276 Zobrazit plný text záznamu View this record from Arxiv