Sciweavers

2905 search results - page 283 / 581
» Learning in Hyperlinked Environments
Sort
View
CORR
2007
Springer
73views Education» more  CORR 2007»
15 years 3 months ago
Universal Reinforcement Learning
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...
Vivek F. Farias, Ciamac Cyrus Moallemi, Tsachy Wei...
AAMAS
2002
Springer
15 years 3 months ago
The Implications of Philosophical Foundations for Knowledge Representation and Learning in Agents
Abstract. The purpose of this research is to show the relevance of philosophical theories to agent knowledge base (AKB) design, implementation, and behaviour. We will describe how ...
Nicholas Lacey, Mark Lee
NN
1998
Springer
117views Neural Networks» more  NN 1998»
15 years 3 months ago
Neural learning of embodied interaction dynamics
This paper presents our approach towards realizing a robot which can bootstrap itself towards higher complexity through embodied interaction dynamics with the environment includin...
Yasuo Kuniyoshi, Luc Berthouze
OSDI
2008
ACM
16 years 3 months ago
An Internet Protocol Address Clustering Algorithm
We pose partitioning a b-bit Internet Protocol (IP) address space as a supervised learning task. Given (IP, property) labeled training data, we develop an IP-specific clustering a...
Robert Beverly, Karen R. Sollins
126
Voted
C5
2006
IEEE
15 years 9 months ago
Idioms for Composing Games with EToys
1 Creating one’s own games has been the main motivation for many people to learn programming. But the barrier to learn a general purpose programming language is very high, espec...
Markus Gälli, Oscar Nierstrasz, Serge Stinckw...