Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning.

Andrea Zanette Martin J. Wainwright

Published in: CoRR (2022)

Keyphrases

efficient learning
learning algorithm
reinforcement learning
cooperative
multi agent
state space
reinforcement learning algorithms
learning rate
bayes net
concept classes
data exchange
model free
data management
membership queries
pattern languages
open source
worst case