Approximate Midpoint Policy Iteration for Linear Quadratic Control.
Benjamin GravellIman ShamesTyler H. SummersPublished in: L4DC (2021)
Keyphrases
- optimal control
- policy iteration
- linear quadratic
- policy evaluation
- infinite horizon
- markov decision processes
- approximate policy iteration
- model free
- reinforcement learning
- least squares
- fixed point
- vector valued
- optimal policy
- dynamical systems
- control strategy
- gaussian model
- temporal difference
- machine learning
- closed loop
- dynamic programming
- control system
- markov decision process
- learning algorithm