Reinforcement learning for optimal control of linear impulsive systems with periodic impulses.
Yan WuShixian LuoFeiqi DengPublished in: Neurocomputing (2024)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- linear quadratic
- dynamic programming
- feedback control
- control strategy
- infinite horizon
- class of nonlinear systems
- risk sensitive
- linear systems
- optimal control problems
- brownian motion
- policy iteration
- average cost
- neural network
- model free
- differential equations
- state space
- learning algorithm