231 search results - page 20 / 47 » Active Learning in Partially Observable Markov Decision Proc... |
SOCIALCOM
2010
13 years 6 months ago
2010
Abstract--In both the commercial and defense sectors a compelling need is emerging for rapid, yet secure, dissemination of information. In this paper we address the threat of infor...
CVPR
2012
IEEE
11 years 11 months ago
2012
IEEE
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
IUI
2010
ACM
14 years 5 months ago
2010
ACM
Most of the previous work on non-invasive brain-computer interfaces (BCIs) has been focused on feature extraction and classification algorithms to achieve high performance for the...
NIPS
2008
13 years 10 months ago
2008
Classical game theoretic approaches that make strong rationality assumptions have difficulty modeling human behaviour in economic games. We investigate the role of finite levels o...
NN
2010
Springer
13 years 3 months ago
2010
Springer
Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...