Sciweavers

UAI
2007
14 years 10 months ago
"I Can Name that Bayesian Network in Two Matrixes!"
The traditional approach to building Bayesian networks is to build the graphical structure using a graphical editor and then add probabilities using a separate spreadsheet for eac...
Russell Almond
ATAL
2008
Springer
14 years 10 months ago
Expediting RL by using graphical structures
The goal of Reinforcement learning (RL) is to maximize reward (minimize cost) in a Markov decision process (MDP) without knowing the underlying model a priori. RL algorithms tend ...
Peng Dai, Alexander L. Strehl, Judy Goldsmith