2861 search results - page 280 / 573 » Parallel Online Learning |
174
click to vote
CVPR
2010
IEEE
15 years 2 months ago
2010
IEEE
This paper shows that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, i.e. data are structured if knowing the ...
131
Voted
PPSN
2004
Springer
15 years 9 months ago
2004
Springer
In Multi-Agent learning, agents must learn to select actions that maximize their utility given the action choices of the other agents. Cooperative Coevolution offers a way to evol...
134
click to vote
GCC
2003
Springer
15 years 9 months ago
2003
Springer
Guided by the cooperation theory, this paper puts forward an interactive and cooperative learning environment design that is based on the self-learning mode and cooperative learnin...
142
click to vote
NIPS
2007
15 years 5 months ago
2007
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
166
click to vote
COLT
2010
Springer
15 years 2 months ago
2010
Springer
In standard online learning, the goal of the learner is to maintain an average loss that is "not too big" compared to the loss of the best-performing function in a fixed...