Reinforcement Learning Control of Constrained Dynamic Systems with Uniformly Ultimate Boundedness Stability Guarantee.
Minghao HanYuan TianLixian ZhangJun WangWei PanPublished in: CoRR (2020)
Keyphrases
- dynamic systems
- discrete event
- reinforcement learning
- complex systems
- linear time invariant
- consistency based diagnosis
- control problems
- qualitative reasoning
- optimal control
- control system
- qualitative models
- dynamical systems
- function approximation
- state variables
- ordinary differential equations
- reinforcement learning algorithms
- continuous variables
- robot control
- temporal difference
- machine learning
- lyapunov function
- control strategies
- sufficient conditions
- state space
- stability analysis
- dynamic programming
- state estimation
- multi agent
- adaptive control
- cooperative