2327 search results - page 123 / 466 » Consistency of functional learning methods based on derivati... |
157
click to vote
NN
1998
Springer
15 years 6 months ago
1998
Springer
We experimented on task-level robot learning based on bi-directional theory. The via-point representation was used for ‘learning by watching’. In our previous work, we had a r...
187
click to vote
COMPIMAGE
2010
Springer
16 years 1 months ago
2010
Springer
We propose a method that we call auto-adaptive convolution which extends the classical notion of convolution in pictures analysis to function analysis on a discrete set. We define...
179
click to vote
ICML
2008
IEEE
16 years 7 months ago
2008
IEEE
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
128
click to vote
SEAL
1998
Springer
15 years 10 months ago
1998
Springer
Abstract. In this paper, we discuss an approach to an operator scheduling problem in a large organization over time with the aim of maintaining service quality and reducing total l...
171
click to vote
CORR
2010
Springer
15 years 5 months ago
2010
Springer
We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...