340 search results - page 50 / 68 » Kernelized value function approximation for reinforcement le... |
148
Voted
ICML
2000
IEEE
16 years 3 months ago
2000
IEEE
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
101
click to vote
WWW
2007
ACM
16 years 3 months ago
2007
ACM
This paper describes a kernel based Web Services (abbreviated as service) matching mechanism for service discovery and integration. The matching mechanism tries to exploit the lat...
119
click to vote
NIPS
1993
15 years 3 months ago
1993
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...
116
click to vote
ICML
1998
IEEE
16 years 3 months ago
1998
IEEE
tion Learning about Temporally Abstract Actions Richard S. Sutton Department of Computer Science University of Massachusetts Amherst, MA 01003-4610 rich@cs.umass.edu Doina Precup D...
126
click to vote
MLCW
2005
Springer
15 years 8 months ago
2005
Springer
In many regression tasks, in addition to an accurate estimate of the conditional mean of the target distribution, an indication of the predictive uncertainty is also required. Ther...