Memory-Efficient Filter Based Novel Policy Iteration Technique for Adaptive LQR.

Sumit Kumar Jha Sayan Basu Roy Shubhendu Bhasin

Published in: ACC (2018)

Keyphrases

memory efficient
policy iteration
markov decision processes
optimal control
fixed point
reinforcement learning
sample path
least squares
optimal policy
model free
average reward
finite state
markov decision process
objective function
infinite horizon
supervised learning
probability distribution
discounted reward