664 search results - page 65 / 133 » Combining Reinforcement Learning with a Local Control Algori... |
159
click to vote
FLAIRS
2009
15 years 2 months ago
2009
In this paper, we investigate the hypothesis that plan recognition can significantly improve the performance of a casebased reinforcement learner in an adversarial action selectio...
118
click to vote
ICML
2008
IEEE
16 years 5 months ago
2008
IEEE
We consider the problem of learning to follow a desired trajectory when given a small number of demonstrations from a sub-optimal expert. We present an algorithm that (i) extracts...
119
click to vote
ICPR
2008
IEEE
16 years 6 months ago
2008
IEEE
We present a hierarchical feature fusion model for image classification that is constructed by an evolutionary learning algorithm. The model has the ability to combine local patch...
153
click to vote
ECCV
2008
Springer
16 years 6 months ago
2008
Springer
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
131
Voted
AI
2002
Springer
15 years 4 months ago
2002
Springer
TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD...