65 search results - page 3 / 13 » Bias and variance in value function estimation |
NIPS
2001
13 years 7 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 ...
TSP
2010
13 years 24 days ago
2010
Abstract--The high-order phase function (HPF) is a useful tool to estimate the instantaneous frequency rate (IFR) of a signal with a polynomial phase. In this paper, the asymptotic...
NIPS
2001
13 years 7 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...
AUSAI
2003
Springer
13 years 9 months ago
2003
Springer
We investigate why discretization is effective in naive-Bayes learning. We prove a theorem that identifies particular conditions under which discretization will result in naiveBay...
PG
2007
IEEE
2007
IEEE
Statistical Hypothesis Testing for Assessing Monte Carlo Estimators: Applications to Image Synthesis
14 years 12 days ago
Image synthesis algorithms are commonly compared on the basis of running times and/or perceived quality of the generated images. In the case of Monte Carlo techniques, assessment ...