567 search results - page 29 / 114 » Regularized Policy Iteration |
110
click to vote
CLA
2007
15 years 1 months ago
2007
The generalization of policies in reinforcement learning is a main issue, both from the theoretical model point of view and for their applicability. However, generalizing from a se...
118
Voted
TIP
2010
14 years 7 months ago
2010
We develop two new algorithms for tomographic reconstruction which incorporate the technique of equally-sloped tomography (EST) and allow for the optimized and flexible implementat...
96
Voted
AAAI
2006
15 years 1 months ago
2006
Planning in partially-observable dynamical systems is a challenging problem, and recent developments in point-based techniques such as Perseus significantly improve performance as...
129
Voted
ECML
2005
Springer
15 years 6 months ago
2005
Springer
This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari...
88
Voted
BIRTHDAY
1997
Springer
15 years 4 months ago
1997
Springer
We study a Lindenmayer-like parallel rewriting system to model the growth of filaments (arrays of cells) in which developmental errors may occur. In essence this model is the fuzz...