91 search results - page 8 / 19 » Event-based control using quadratic approximate value functi... |
ICML
2000
IEEE
14 years 8 months ago
2000
IEEE
This paper presents a general method to derive tight rates of convergence for numerical approximations in optimal control when we consider variable resolution grids. We study the ...
UAI
2008
13 years 9 months ago
2008
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...
FOGA
2011
12 years 11 months ago
2011
The distribution of fitness values across a set of states sharply influences the dynamics of evolutionary processes and heuristic search in combinatorial optimization. In this p...
ICPR
2006
IEEE
14 years 8 months ago
2006
IEEE
To accelerate the learning of reinforcement learning, many types of function approximation are used to represent state value. However function approximation reduces the accuracy o...
ICML
1996
IEEE
14 years 8 months ago
1996
IEEE
Some of the most successful recent applications of reinforcement learning have used neural networks and the TD algorithm to learn evaluation functions. In this paper, we examine t...