Sciweavers

680 search results - page 78 / 136
» Intrinsically Motivated Machines
Sort
View
ICML
2003
IEEE
14 years 1 months ago
The Influence of Reward on the Speed of Reinforcement Learning: An Analysis of Shaping
Shaping can be an effective method for improving the learning rate in reinforcement systems. Previously, shaping has been heuristically motivated and implemented. We provide a for...
Adam Laud, Gerald DeJong
COLT
2003
Springer
14 years 1 months ago
Maximum Margin Algorithms with Boolean Kernels
Recent work has introduced Boolean kernels with which one can learn linear threshold functions over a feature space containing all conjunctions of length up to k (for any 1 ≤ k ...
Roni Khardon, Rocco A. Servedio
ICPP
2002
IEEE
14 years 1 months ago
Linux/SimOS - A Simulation Environment for Evaluating High-Speed Communication Systems
This paper presents Linux/SimOS, a Linux operating system port to SimOS, which is a complete machine simulator from Stanford. The motivation for Linux/SimOS is to alleviate the li...
Chulho Won, Ben Lee, Chansu Yu, Sangman Moh, Yong-...
COLT
2000
Springer
14 years 13 days ago
Entropy Numbers of Linear Function Classes
This paper collects together a miscellany of results originally motivated by the analysis of the generalization performance of the “maximum-margin” algorithm due to Vapnik and...
Robert C. Williamson, Alex J. Smola, Bernhard Sch&...
SIGIR
1999
ACM
14 years 12 days ago
Information Retrieval as Statistical Translation
We propose a new probabilistic approach to information retrieval based upon the ideas and methods of statistical machine translation. The central ingredient in this approach is a ...
Adam L. Berger, John D. Lafferty