Sciweavers

301 search results - page 42 / 61
» Approximate predictive state representations
Sort
View
PAMI
2007
214views more  PAMI 2007»
13 years 7 months ago
Tracking Deforming Objects Using Particle Filtering for Geometric Active Contours
—Tracking deforming objects involves estimating the global motion of the object and its local deformations as a function of time. Tracking algorithms using Kalman filters or part...
Yogesh Rathi, Namrata Vaswani, Allen Tannenbaum, A...
ICML
2002
IEEE
14 years 8 months ago
Algorithm-Directed Exploration for Model-Based Reinforcement Learning in Factored MDPs
One of the central challenges in reinforcement learning is to balance the exploration/exploitation tradeoff while scaling up to large problems. Although model-based reinforcement ...
Carlos Guestrin, Relu Patrascu, Dale Schuurmans
ICDE
2003
IEEE
211views Database» more  ICDE 2003»
14 years 9 months ago
Capturing Sensor-Generated Time Series with Quality Guarantees
We are interested in capturing time series generated by small wireless electronic sensors. Battery-operated sensors must avoid heavy use of their wireless radio which is a key cau...
Iosif Lazaridis, Sharad Mehrotra
SIGGRAPH
2010
ACM
13 years 11 months ago
Physical reproduction of materials with specified subsurface scattering
We investigate a complete pipeline for measuring, modeling, and fabricating objects with specified subsurface scattering behaviors. The process starts with measuring the scatterin...
Miloš Hašan, Martin Fuchs, Wojciech Matusik, Han...
NIPS
2001
13 years 9 months ago
Model-Free Least-Squares Policy Iteration
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Michail G. Lagoudakis, Ronald Parr