132 search results - page 4 / 27 » Generalization in Reinforcement Learning: Safely Approximati... |
ATAL
2008
Springer
13 years 9 months ago
2008
Springer
Reinforcement Learning research is traditionally devoted to solve single-task problems. Therefore, anytime a new task is faced, learning must be restarted from scratch. Recently, ...
ESANN
2006
13 years 8 months ago
2006
We focus on neuro-dynamic programming methods to learn state-action value functions and outline some of the inherent problems to be faced, when performing reinforcement learning in...
ICPR
2006
IEEE
14 years 8 months ago
2006
IEEE
To accelerate the learning of reinforcement learning, many types of function approximation are used to represent state value. However function approximation reduces the accuracy o...
ECML
2004
Springer
14 years 15 days ago
2004
Springer
Abstract. We present first experiments using Support Vector Regression as function approximator for an on-line, sarsa-like reinforcement learner. To overcome the batch nature of S...
ICML
1996
IEEE
13 years 11 months ago
1996
IEEE
This paper presents a direct reinforcement learning algorithm, called Finite-Element Reinforcement Learning, in the continuous case, i.e. continuous state-space and time. The eval...