Sciweavers

74 search results - page 4 / 15
» Stochastic search using the natural gradient
Sort
View
PPSN
2010
Springer
13 years 9 months ago
A Natural Evolution Strategy for Multi-objective Optimization
Abstract. The recently introduced family of natural evolution strategies (NES), a novel stochastic descent method employing the natural gradient, is providing a more principled alt...
Tobias Glasmachers, Tom Schaul, Jürgen Schmid...
GECCO
2010
Springer
230views Optimization» more  GECCO 2010»
14 years 3 months ago
Exponential natural evolution strategies
The family of natural evolution strategies (NES) offers a principled approach to real-valued evolutionary optimization by following the natural gradient of the expected fitness....
Tobias Glasmachers, Tom Schaul, Yi Sun, Daan Wiers...
ICML
2000
IEEE
14 years 11 months ago
Reinforcement Learning in POMDP's via Direct Gradient Ascent
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
Jonathan Baxter, Peter L. Bartlett
CEC
2008
IEEE
14 years 5 months ago
Natural Evolution Strategies
— This paper presents Natural Evolution Strategies (NES), a novel algorithm for performing real-valued ‘black box’ function optimization: optimizing an unknown objective func...
Daan Wierstra, Tom Schaul, Jan Peters, Jürgen...
JMLR
2006
124views more  JMLR 2006»
13 years 10 months ago
Policy Gradient in Continuous Time
Policy search is a method for approximately solving an optimal control problem by performing a parametric optimization search in a given class of parameterized policies. In order ...
Rémi Munos