D3PI: Data-Driven Distributed Policy Iteration for Homogeneous Interconnected Systems.

Siavash Alemzadeh Shahriar Talebi Mehran Mesbahi

Published in: CoRR (2021)

Keyphrases

data driven
policy iteration
search algorithm
markov decision processes
fixed point
model free
bayesian networks
reinforcement learning
least squares
convergence rate