1235 search results - page 4 / 247 » ABC Reinforcement Learning |
ECML
2003
Springer
14 years 3 months ago
2003
Springer
We present in this paper a method to introduce a priori knowledge into reinforcement learning using temporally extended actions. The aim of our work is to reduce the learning time ...
CAEPIA
2011
Springer
12 years 9 months ago
2011
Springer
In this paper we apply the recent notion of anytime universal intelligence tests to the evaluation of a popular reinforcement learning algorithm, Q-learning. We show that a general...
CVPR
2012
IEEE
12 years 6 days ago
2012
IEEE
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
AAAI
2012
12 years 5 days ago
2012
Markov decision processes (MDPs) are an established framework for solving sequential decision-making problems under uncertainty. In this work, we propose a new method for batchmod...
AAAI
2011
12 years 9 months ago
2011
We describe the Fourier Basis, a linear value function approximation scheme based on the Fourier Series. We empirically evaluate its properties, and demonstrate that it performs w...