Visualization and Intelligent Systems Laboratory
VISLab

 

 

Contact Information

VISLab
Winston Chung Hall Room 216
University of California, Riverside
900 University Avenue
Riverside, CA 92521-0425


Tel: (951)-827-3954

CRIS
Bourns College of Engineering
UCR
NSF IGERT on Video Bioinformatics

UCR Collaborators:
CSE
ECE
ME
STAT
PSYC
ENTM
BIOL
BPSC
ECON
MATH
BIOENG
MGNT

Other Collaborators:
Keio University

Other Activities:
IEEE Biometrics Workshop 2014
IEEE Biometrics Workshop 2013
Worshop on DVSN 2009
Multibiometrics Book

Webmaster Contact Information:
Alex Shin
wshin@ece.ucr.edu

Last updated: July 1, 2017

 

 

Extended Q-Learning

Presented by: Pat Leang

ABSTRACT: Reinforcement learning methods are based on the mapping of state space to an action space. The mapping is done via sensing of environmental input. Errors are then the result of state space sampling. An approach called Extended Q-learning (EQ-learning) is implemented to overcome this error. In this approach, weighted base functions are formed which approximates a continuious value, appropriate for the continuous sensor values obtained from the autonomous robot. The approach is based on stochastic field model and promises to improve learning performance over ordinary learning methods.