Sciweavers

811 search results - page 105 / 163
» Avoiding Approximate Squares
Sort
View
ICPR
2006
IEEE
14 years 10 months ago
Control Double Inverted Pendulum by Reinforcement Learning with Double CMAC Network
To accelerate the learning of reinforcement learning, many types of function approximation are used to represent state value. However function approximation reduces the accuracy o...
Siwei Luo, Yu Zheng, Ziang Lv
ICML
2003
IEEE
14 years 9 months ago
BL-WoLF: A Framework For Loss-Bounded Learnability In Zero-Sum Games
We present BL-WoLF, a framework for learnability in repeated zero-sum games where the cost of learning is measured by the losses the learning agent accrues (rather than the number...
Vincent Conitzer, Tuomas Sandholm
ICCAD
2004
IEEE
107views Hardware» more  ICCAD 2004»
14 years 5 months ago
Computation of signal threshold crossing times directly from higher order moments
—This paper introduces a simple method for calculating the times at which any signal crosses a prespecified threshold voltage (e.g., 10%, 20%, 50%, etc.) directly from the moment...
Yehea I. Ismail, Chirayu S. Amin
ICRA
2008
IEEE
134views Robotics» more  ICRA 2008»
14 years 3 months ago
An optimal filtering algorithm for non-parametric observation models in robot localization
— The lack of a parameterized observation model in robot localization using occupancy grids requires the application of sampling-based methods, or particle filters. This work ad...
Jose-Luis Blanco, Javier Gonzalez, Juan-Antonio Fe...
3DPVT
2006
IEEE
155views Visualization» more  3DPVT 2006»
14 years 3 months ago
The Reverse Projection Correlation Principle for Depth from Defocus
In this paper, we address the problem of finding depth from defocus in a fundamentally new way. Most previous methods have used an approximate model in which blurring is shift in...
Scott McCloskey, Michael S. Langer, Kaleem Siddiqi