Sign in
A Promoting Method of Role Differentiation using a Learning Rate that has a Periodically Negative Value in Multi-agent Reinforcement Learning.
Masato Nagayoshi
Simon J. H. Elderton
Hisashi Tamaki
Published in:
J. Robotics Netw. Artif. Life (2020)
Keyphrases
</>
learning rate
rapid convergence
optimization algorithm
high accuracy
multi agent reinforcement learning
cooperative
support vector
learning process
evolutionary algorithm
fuzzy neural network