827 search results - page 52 / 166 » Variational methods for Reinforcement Learning |
ICCBR
2009
Springer
14 years 2 months ago
2009
Springer
Positive transfer learning (TL) occurs when, after gaining experience from learning how to solve a (source) task, the same learner can exploit this experience to improve performanc...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
In this work a new online learning algorithm that uses automatic relevance determination (ARD) is proposed for fast adaptive nonlinear filtering. A sequential decision rule for i...
IJCNN
2006
IEEE
14 years 1 months ago
2006
IEEE
— In many applications of supervised learning, the conditional average of the target variables is not sufficient for prediction. The dependencies between the explanatory variabl...
NIPS
2001
13 years 9 months ago
2001
We combine the replica approach from statistical physics with a variational approach to analyze learning curves analytically. We apply the method to Gaussian process regression. A...
CEC
2005
IEEE
13 years 9 months ago
2005
IEEE
We apply XCS with computed prediction (XCSF) to tackle multistep reinforcement learning problems involving continuous inputs. In essence we use XCSF as a method of generalized rein...