Sciweavers

CIG
2005
IEEE
14 years 6 months ago
Nannon: A Nano Backgammon for Machine Learning Research
A newly designed game is introduced, which feels like Backgammon, but has a simplified rule set. Unlike earlier attempts at simplifying the game, Nannon maintains enough features a...
Jordan B. Pollack
ICRA
2007
IEEE
155views Robotics» more  ICRA 2007»
14 years 6 months ago
Value Function Approximation on Non-Linear Manifolds for Robot Motor Control
— The least squares approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular an...
Masashi Sugiyama, Hirotaka Hachiya, Christopher To...
ICML
1998
IEEE
15 years 1 months ago
Value Function Based Production Scheduling
Production scheduling, the problem of sequentially con guring a factory to meet forecasted demands, is a critical problem throughout the manufacturing industry. The requirement of...
Jeff G. Schneider, Justin A. Boyan, Andrew W. Moor...
ICML
2007
IEEE
15 years 1 months ago
Learning state-action basis functions for hierarchical MDPs
This paper introduces a new approach to actionvalue function approximation by learning basis functions from a spectral decomposition of the state-action manifold. This paper exten...
Sarah Osentoski, Sridhar Mahadevan