60 search results - page 2 / 12 » Revisiting Natural Actor-Critics with Value Function Approxi... |
DFG
2007
Springer
13 years 11 months ago
2007
Springer
: The concept of natural neighbors employs the notion of distance to define local neighborhoods in discrete data. Especially when querying and accessing large scale data, it is im...
TSMC
2008
13 years 4 months ago
2008
This paper describes several ensemble methods that combine multiple different reinforcement learning (RL) algorithms in a single agent. The aim is to enhance learning speed and fin...
ICML
2007
IEEE
14 years 5 months ago
2007
IEEE
Basis functions derived from an undirected graph connecting nearby samples from a Markov decision process (MDP) have proven useful for approximating value functions. The success o...
ECCV
2006
Springer
13 years 8 months ago
2006
Springer
The formulation of trace quotient is shared by many computer vision problems; however, it was conventionally approximated by an essentially different formulation of quotient trace,...
ECML
2004
Springer
13 years 10 months 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...