A Lyapunov approach for stable reinforcement learning.
Julio B. ClempnerPublished in: Comput. Appl. Math. (2022)
Keyphrases
- reinforcement learning
- equilibrium point
- adaptive control
- stability analysis
- state space
- function approximation
- temporal difference
- machine learning
- exponential stability
- reinforcement learning algorithms
- model free
- class of nonlinear systems
- asymptotic stability
- sufficient conditions
- control scheme
- learning algorithm
- multi agent
- control theory
- optimal policy
- action selection
- transfer learning
- nonlinear systems
- robotic control
- markov decision processes
- learning agent
- optimal control
- control law
- genetic algorithm
- robust stability
- learning classifier systems
- multi agent reinforcement learning
- lyapunov function
- reinforcement learning methods
- nonlinear dynamics
- dynamic environments
- dynamical systems