56 search results - page 1 / 12 » A k-NN Based Perception Scheme for Reinforcement Learning |
EUROCAST
2007
Springer
13 years 10 months ago
2007
Springer
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
CVPR
2012
IEEE
11 years 7 months ago
2012
IEEE
The k-NN graph has played a central role in increasingly popular data-driven techniques for various learning and vision tasks; yet, finding an efficient and effective way to con...
GLOBECOM
2008
IEEE
13 years 11 months ago
2008
IEEE
—MIMO-OFDM wireless systems require adaptive modulation and coding based on channel state information (CSI) to maximize throughput in changing wireless channels. Traditional adap...
FGR
2008
IEEE
13 years 4 months ago
2008
IEEE
In this paper, we address the recognition of subtle facial expressions by reasoning on the classification confidence. Psychological evidences have determined that eyelids and eyeb...
NN
2002
Springer
13 years 4 months ago
2002
Springer
In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...