News for hackers. Stuff that matters.
Re:Reinforcement Learning and Optimal Control by Jack000 on Saturday February 23, 2019 @09:12PM (#19236718)
for linear systems modern control theory is already optimal (?) so given a linear system I'd assume an RL method would just approximate the optimal control method. I think the potential for RL methods is in capturing nonlinearities in actuators like artificial muscle.
Re:Reinforcement Learning and Optimal Control by dpandya on Sunday February 24, 2019 @12:46AM (#19237329)
I meant applying a linear approximation.