Sign in
Adaptive Step-Size for Policy Gradient Methods.
Matteo Pirotta
Marcello Restelli
Luca Bascetta
Published in:
NIPS (2013)
Keyphrases
</>
step size
variable step size
convergence rate
convergence speed
cost function
policy gradient methods
actor critic
approximate dynamic programming
temporal difference
gradient method
multi agent
computational complexity
natural actor critic