536 search results - page 14 / 108 » Residual Algorithms: Reinforcement Learning with Function Ap... |
ICML
2000
IEEE
14 years 8 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
IJON
2006
13 years 7 months ago
2006
In this work, we propose a variation of a direct reinforcement learning algorithm, suitable for usage with spiking neurons based on the spike response model (SRM). The SRM is a bi...
AAAI
1998
13 years 9 months ago
1998
In this paper, we describe methods for e ciently computing better solutions to control problems in continuous state spaces. We provide algorithms that exploit online search to boo...
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...
SDM
2010
SIAM
13 years 9 months ago
2010
SIAM
In recent years, matrix approximation for missing value prediction has emerged as an important problem in a variety of domains such as recommendation systems, e-commerce and onlin...