Approximation Error Back-Propagation for Q-Function in Scalable Reinforcement Learning with Tree Dependence Structure.

Yuzi Yan Yu Dong Kai Ma Yuan Shen

Published in: ICASSP (2023)

Keyphrases

dependence structure
reinforcement learning
error back propagation
multi layer
feed forward
state space
dynamic programming
neural network
back propagation
multiresolution
artificial intelligence
knn
markov decision processes
expert systems
learning scheme
markov networks
marginal distributions
learning algorithm