H ∞ Control Synthesis for Linear Parabolic PDE Systems with Model-Free Policy Iteration.
Biao LuoDerong LiuXiong YangHongwen MaPublished in: ISNN (2015)
Keyphrases
- model free
- policy iteration
- reinforcement learning
- markov decision processes
- reinforcement learning algorithms
- impedance control
- temporal difference
- function approximation
- policy evaluation
- sample path
- least squares
- optimal control
- fixed point
- optimal policy
- average reward
- infinite horizon
- active learning
- finite number
- finite state
- markov decision problems
- neural network