Policy Iteration for Linear Quadratic Games With Stochastic Parameters.
Benjamin GravellKarthik GanapathyTyler H. SummersPublished in: IEEE Control. Syst. Lett. (2021)
Keyphrases
- linear quadratic
- policy iteration
- optimal control
- sample path
- markov decision processes
- closed loop
- vector valued
- model free
- dynamical systems
- fixed point
- reinforcement learning
- infinite horizon
- training data
- temporal difference
- computer vision
- gaussian model
- markov decision process
- search algorithm
- evaluation function
- least squares