The Blessing of Heterogeneity in Federated Q-learning: Linear Speedup and Beyond.

Jiin Woo Gauri Joshi Yuejie Chi

Published in: CoRR (2023)

Keyphrases

orders of magnitude
reinforcement learning
learning algorithm
multi agent
cooperative
data sources
state space
dynamic environments
database
real time
neural network
artificial neural networks
least squares
optimal policy
learning rate
action selection