51 search results - page 7 / 11 » Exponentiated Gradient Methods for Reinforcement Learning |
RAS
2006
13 years 7 months ago
2006
A class of biped locomotion called Passive Dynamic Walking (PDW) has been recognized to be efficient in energy consumption and a key to understand human walking. Although PDW is s...
NN
2010
Springer
13 years 6 months ago
2010
Springer
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
GECCO
2009
Springer
13 years 5 months ago
2009
Springer
The covariance matrix adaptation evolution strategy (CMAES) has proven to be a powerful method for reinforcement learning (RL). Recently, the CMA-ES has been augmented with an ada...
GECCO
2006
Springer
13 years 11 months ago
2006
Springer
This paper investigates reinforcement learning (RL) in XCS. First, it formally shows that XCS implements a method of generalized RL based on linear approximators, in which the usu...
IWLCS
2005
Springer
14 years 1 months ago
2005
Springer
Aiming to clarify the convergence or divergence conditions for Learning Classifier System (LCS), this paper explores: (1) an extreme condition where the reinforcement process of ...