164 search results - page 29 / 33 » Self-Optimizing Memory Controllers: A Reinforcement Learning... |
ICML
1994
IEEE
13 years 11 months ago
1994
IEEE
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
NIPS
2001
13 years 8 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
GECCO
2008
Springer
13 years 8 months ago
2008
Springer
Legged robots are useful in tasks such as search and rescue because they can effectively navigate on rugged terrain. However, it is difficult to design controllers for them that ...
JSAC
2007
13 years 7 months ago
2007
— One of the distinctive features in a wireless ad hoc network is lack of any central controller or single point of authority, in which each node/link then makes its own decision...
EMNLP
2011
12 years 7 months ago
2011
We propose a general method to watermark and probabilistically identify the structured outputs of machine learning algorithms. Our method is robust to local editing operations and...