Probabilistic Generalization of Simple Grammars and Its Application to Reinforcement Learning.

Takeshi Shibata Ryo Yoshinaka Takashi Chikayama

Published in: ALT (2006)

Keyphrases

reinforcement learning
probabilistic model
data driven
function approximation
data sets
multi agent
state space
neural network
decision trees
natural language
optimal policy
learning tasks
belief networks
context free