Emergence of Prediction by Reinforcement Learning Using a Recurrent Neural Network.

Kenta Goto Katsunari Shibata

Published in: J. Robotics (2010)

Keyphrases

reinforcement learning
prediction accuracy
learning algorithm
function approximation
reinforcement learning algorithms
artificial intelligence
learning process
state space
optimal policy
prediction model
real time
neural network
dynamic programming
model free
prediction algorithm
robotic control