123
Voted
UAI
2007
15 years 1 months ago
2007
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...
88
Voted
ATAL
2008
Springer
15 years 2 months ago
2008
Springer
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 ...