Reinforcement learning control of constrained dynamic systems with uniformly ultimate boundedness stability guarantee.
Minghao HanYuan TianLixian ZhangJun WangWei PanPublished in: Autom. (2021)
Keyphrases
- dynamic systems
- discrete event
- reinforcement learning
- complex systems
- linear time invariant
- control problems
- qualitative reasoning
- dynamical systems
- consistency based diagnosis
- control system
- state variables
- robot control
- function approximation
- optimal control
- control method
- model based diagnosis
- learning algorithm
- ordinary differential equations
- state estimation
- qualitative models
- adaptive control
- control strategy
- control policy
- lyapunov function
- model free
- dynamic programming
- multi agent systems
- markov decision processes
- optimal policy
- multi agent
- feedback control
- sufficient conditions
- particle filter
- state space