Approximate Midpoint Policy Iteration for Linear Quadratic Control.
Benjamin GravellIman ShamesTyler H. SummersPublished in: CoRR (2020)
Keyphrases
- optimal control
- policy iteration
- linear quadratic
- policy evaluation
- markov decision processes
- reinforcement learning
- infinite horizon
- vector valued
- control strategy
- control system
- model free
- optimal policy
- closed loop
- dynamical systems
- dynamic programming
- finite state
- least squares
- approximate policy iteration
- real time
- temporal difference
- probabilistic model
- learning algorithm
- neural network