Sciweavers

2082 search results - page 233 / 417
» Using model knowledge for learning inverse dynamics
Sort
View
ATAL
2005
Springer
15 years 9 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
VR
2008
IEEE
202views Virtual Reality» more  VR 2008»
15 years 3 months ago
FARMTASIA: an online game-based learning environment based on the VISOLE pedagogy
Virtual interactive student-oriented learning environment (VISOLE) is a game-based constructivist pedagogical approach that encompasses the creation of an online interactive world ...
Kevin K. F. Cheung, Morris Siu Yung Jong, Fong Lok...
CUZA
2002
129views more  CUZA 2002»
15 years 3 months ago
Ad Hoc Metacomputing with Compeer
Metacomputing allows the exploitation of geographically seperate, heterogenous networks and resources. Most metacomputers are feature rich and carry a long, complicated installati...
Keith Power, John P. Morrison
ICCV
2009
IEEE
16 years 9 months ago
Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets
We present an approach to visual tracking based on dividing a target into multiple regions, or fragments. The target is represented by a Gaussian mixture model in a joint feature...
Prakash Chockalingam, Nalin Pradeep
ICCS
2005
Springer
15 years 9 months ago
Dynamic Data Driven Coupling of Continuous and Discrete Methods for 3D Tracking
We present a new framework for robust 3D tracking, using a dynamic data driven coupling of continuous and discrete methods to overcome their limitations. Our method uses primarily ...
Dimitris N. Metaxas, Gabriel Tsechpenakis