Model-Free λ-Policy Iteration for Discrete-Time Linear Quadratic Regulation.
Yongliang YangBahare KiumarsiHamidreza ModaresChengzhong XuPublished in: IEEE Trans. Neural Networks Learn. Syst. (2023)
Keyphrases
- linear quadratic
- policy iteration
- model free
- optimal control
- reinforcement learning
- closed loop
- vector valued
- dynamical systems
- function approximation
- reinforcement learning algorithms
- average reward
- temporal difference
- policy evaluation
- gaussian model
- markov decision problems
- control system
- fixed point
- infinite horizon
- artificial neural networks
- learning algorithm
- dynamic programming
- markov decision processes
- step size
- neural network
- training data
- control strategy
- machine learning