3718 search results - page 181 / 744 » On learning with dissimilarity functions |
208
click to vote
ECML
2006
Springer
15 years 9 months ago
2006
Springer
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
176
click to vote
CVPR
2000
IEEE
16 years 8 months ago
2000
IEEE
?Gibbsian fields or Markov random fields are widely used in Bayesian image analysis, but learning Gibbs models is computationally expensive. The computational complexity is pronoun...
149
click to vote
ICML
2003
IEEE
16 years 6 months ago
2003
IEEE
An important issue in reinforcement learning is how to incorporate expert knowledge in a principled manner, especially as we scale up to real-world tasks. In this paper, we presen...
178
click to vote
ATAL
2007
Springer
16 years 5 days ago
2007
Springer
It is known that the complexity of the reinforcement learning algorithms, such as Q-learning, may be exponential in the number of environment’s states. It was shown, however, th...
152
click to vote
ISMIR
2004
Springer
15 years 11 months ago
2004
Springer
We describe an efficient learning algorithm for aligning a symbolic representation of a musical piece with its acoustic counterpart. Our method employs a supervised learning appr...