Sciweavers

2103 search results - page 181 / 421
» Approximate Learning of Dynamic Models
Sort
View
NIPS
2000
15 years 6 months ago
Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task
The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product o...
Brian Sallans, Geoffrey E. Hinton
ICARCV
2008
IEEE
170views Robotics» more  ICARCV 2008»
15 years 11 months ago
Mixed state estimation for a linear Gaussian Markov model
— We consider a discrete-time dynamical system with Boolean and continuous states, with the continuous state propagating linearly in the continuous and Boolean state variables, a...
Argyris Zymnis, Stephen P. Boyd, Dimitry M. Gorine...
233
Voted

Book
778views
17 years 3 months ago
Gaussian Processes for Machine Learning
"Gaussian processes (GPs) provide a principled, practical, probabilistic approach to learning in kernel machines. GPs have received increased attention in the machine-learning...
Carl Edward Rasmussen and Christopher K. I. Willia...
MABS
1998
Springer
15 years 9 months ago
ABCDE: Agent Based Chaotic Dynamic Emergence
This paper concerns agent based experiments in the field of negotiation and exchange simulation. A computer simulation environment is built, showing the emergence of chaotic price ...
Pietro Terna
ICCV
1999
IEEE
16 years 7 months ago
Higher Order Statistical Learning for Vehicle Detection in Images
The paper describes a scheme for detecting vehicles in images. The proposed method approximately models the unknown distribution of the images of vehicles by learning higher order...
A. N. Rajagopalan, Philippe Burlina, Rama Chellapp...