Sign in
Multi-agent off-policy actor-critic algorithm for distributed multi-task reinforcement learning.
Milos S. Stankovic
Marko Beko
Nemanja Ilic
Srdjan S. Stankovic
Published in:
Eur. J. Control (2023)
Keyphrases
</>
reinforcement learning
multi agent
actor critic
dynamic programming
learning algorithm
multi task
objective function
policy gradient
support vector
model free
approximate dynamic programming
machine learning
multi agent systems
feature extraction
image classification
convergence rate
long run
average reward