Federated Reinforcement Learning for Training Control Policies on Multiple IoT Devices.

Hyun-Kyo Lim Ju-Bong Kim Joo-Seong Heo Youn-Hee Han

Published in: Sensors (2020)

Keyphrases

control policies
reinforcement learning
optimal policy
action space
control policy
continuous state
state space
supervised learning
control strategies
stochastic optimization problems
machine learning
multi agent
path planning
model free