AIPS
2011
12 years 11 months ago
2011
Research in efficient methods for solving infinite-horizon MDPs has so far concentrated primarily on discounted MDPs and the more general stochastic shortest path problems (SSPs...
CORR
2010
Springer
13 years 7 months ago
2010
Springer
We study the convergence of Markov Decision Processes made of a large number of objects to optimization problems on ordinary differential equations (ODE). We show that the optimal...
ICML
2010
IEEE
13 years 8 months ago
2010
IEEE
Standard Reinforcement Learning (RL) aims to optimize decision-making rules in terms of the expected return. However, especially for risk-management purposes, other criteria such ...