13 search results - page 2 / 3 » Model-free reinforcement learning as mixture learning |
ICMLA
2010
13 years 3 months ago
2010
Abstract-- Policy Gradients with Parameter-based Exploration (PGPE) is a novel model-free reinforcement learning method that alleviates the problem of high-variance gradient estima...
NIPS
2008
13 years 6 months ago
2008
We use graphical models and structure learning to explore how people learn policies in sequential decision making tasks. Studies of sequential decision-making in humans frequently...
ML
2002
ACM
13 years 5 months ago
2002
ACM
Solving in an efficient manner many different optimal control tasks within the same underlying environment requires decomposing the environment into its computationally elemental ...
EWCBR
2008
Springer
13 years 7 months ago
2008
Springer
To meet time constraints, a CBR system must control the time spent searching in the case base for a solution. In this paper, we presents the results of a case study comparing the p...
CCIA
2010
Springer
13 years 10 days ago
2010
Springer
Locally weighted as well as Gaussian mixtures learning algorithms are suitable strategies for trajectory learning and skill acquisition, in the context of programming by demonstrat...