13 search results - page 3 / 3 » Rollout Sampling Approximate Policy Iteration |
JMLR
2006
2006
Geometric Variance Reduction in Markov Chains: Application to Value Function and Gradient Estimation
13 years 4 months ago
We study a sequential variance reduction technique for Monte Carlo estimation of functionals in Markov Chains. The method is based on designing sequential control variates using s...
CORR
2010
Springer
13 years 4 months ago
2010
Springer
Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds. We propose a new approximate bili...
CORR
2006
Springer
13 years 4 months ago
2006
Springer
This paper addresses the issue of policy evaluation in Markov Decision Processes, using linear function approximation. It provides a unified view of algorithms such as TD(), LSTD()...