Closing the gap between SVRG and TD-SVRG with Gradient Splitting.

Arsenii Mustafin Alex Olshevsky Ioannis Ch. Paschalidis

Published in: CoRR (2022)

Keyphrases

reinforcement learning
temporal difference
temporal difference learning
td learning
morphological operators
learning algorithm
edge detection
data sets
bayesian networks
reinforcement learning algorithms
gradient method
gradient field
steepest ascent