Login / Signup
A Temporal Difference GNG-Based Algorithm That Can Learn to Control in Reinforcement Learning Environments.
Davi C. de L. Vieira
Paulo J. L. Adeodato
Paulo M. Goncalves Junior
Published in:
ICMLA (1) (2013)
Keyphrases
</>
learning algorithm
dynamic programming
reinforcement learning
search space
model free
cost function
data mining
objective function
temporal difference
decision making
td learning
neural network
machine learning
learning environment
monte carlo