3 search results - page 1 / 1 » Geometric Variance Reduction in Markov Chains: Application t... |
JMLR
2006
2006
Geometric Variance Reduction in Markov Chains: Application to Value Function and Gradient Estimation
13 years 5 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...
NIPS
2001
13 years 6 months ago
2001
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
CIMAGING
2008
13 years 6 months ago
2008
We present an algorithm to generate samples from probability distributions on the space of curves. Traditional curve evolution methods use gradient descent to find a local minimum...