236 search results - page 1 / 48 » Bias and Variance Approximation in Value Function Estimates |
MANSCI
2007
13 years 5 months ago
2007
ICML
2004
IEEE
13 years 10 months ago
2004
IEEE
AAAI
2008
13 years 7 months ago
2008
Off-policy reinforcement learning is aimed at efficiently reusing data samples gathered in the past, which is an essential problem for physically grounded AI as experiments are us...
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
We address two open theoretical questions in Policy Gradient Reinforcement Learning. The first concerns the efficacy of using function approximation to represent the state action ...