90 search results - page 8 / 18 » Geodesic Gaussian kernels for value function approximation |
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
This paper presents a novel framework called proto-reinforcement learning (PRL), based on a mathematical model of a proto-value function: these are task-independent basis function...
AAAI
2010
13 years 9 months ago
2010
We present the design and analysis of an approximately incentive-compatible combinatorial auction. In just a single run, the auction is able to extract enough value information fr...
ACCV
2006
Springer
14 years 1 months ago
2006
Springer
Abstract. To develop statistical models for shapes, we utilize an elastic string representation where curves (denoting shapes) can bend and locally stretch (or compress) to optimal...
Book
"Gaussian processes (GPs) provide a principled, practical, probabilistic approach to learning in kernel machines. GPs have received increased attention in the machine-learning...
ICML
2007
IEEE
14 years 8 months ago
2007
IEEE
We1 present a new actor-critic learning model in which a Bayesian class of non-parametric critics, using Gaussian process temporal difference learning is used. Such critics model ...