Pseudorehearsal in Value Function Approximation.

Vladimir Marochko Leonard Johard Manuel Mazzara

Published in: KES-AMSTA (2017)

Keyphrases

basis functions
state space
approximate dynamic programming
temporal difference
temporal difference learning
pattern recognition
state action
neural network
learning algorithm
reinforcement learning
multi agent
learning environment
artificial neural networks
special case
linear combination
monte carlo