127 search results - page 13 / 26 » Online Methods for Multi-Domain Learning and Adaptation |
JMLR
2010
13 years 2 months ago
2010
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...
ICPR
2008
IEEE
14 years 8 months ago
2008
IEEE
Online Boosting is an effective incremental learning method which can update weak classifiers efficiently according to the object being trackedt. It is a promising technique for o...
ICRA
2003
IEEE
14 years 27 days ago
2003
IEEE
s - For the on-line safe path planning of a mobile robot in unknown environments, the paper proposes a simple Hopfield Neural Network ( HNN ) planner. Without learning process, the...
KES
2004
Springer
14 years 29 days ago
2004
Springer
This paper presents a novel method for on-line coordination in multiagent reinforcement learning systems. In this method a reinforcement-learning agent learns to select its action ...
CVPR
2003
IEEE
14 years 27 days ago
2003
IEEE
Relevance feedback has been an indispensable component for multimedia retrieval systems. In this paper, we present an adaptive pattern discovery method, which addresses relevance ...