192 search results - page 17 / 39 » Knowledge States: A Tool for Randomized Online Algorithms |
AAAI
1993
13 years 9 months ago
1993
This paper analyzes the complexity of on-line reinforcement learning algorithms, namely asynchronous realtime versions of Q-learning and value-iteration, applied to the problem of...
TC
2008
13 years 8 months ago
2008
Network structure construction and global state maintenance are expensive in large-scale, dynamic peer-to-peer (p2p) networks. With inherent topology independence and low state mai...
SDM
2009
SIAM
14 years 5 months ago
2009
SIAM
This paper proposes Twin Vector Machine (TVM), a constant space and sublinear time Support Vector Machine (SVM) algorithm for online learning. TVM achieves its favorable scaling b...
ATAL
2011
Springer
12 years 8 months ago
2011
Springer
Plug-in hybrid electric vehicles are expected to place a considerable strain on local electricity distribution networks, requiring charging to be coordinated in order to accommoda...
FIW
2007
13 years 10 months ago
2007
Feature interaction detection methods, whether online or offline, depend on previous knowledge of conflicts between the actions executed by the features. This knowledge is usually ...