Login / Signup
Balancing Learning Speed and Stability in Policy Gradient via Adaptive Exploration.
Matteo Papini
Andrea Battistello
Marcello Restelli
Published in:
AISTATS (2020)
Keyphrases
</>
learning speed
policy gradient
feed forward neural networks
rbf network
actor critic
activation function
function approximation
neural network
feature extraction
reinforcement learning
back propagation
input output
feed forward
variance reduction