Model-Free Global Stabilization of Discrete-Time Linear Systems with Saturating Actuators Using Reinforcement Learning.
Syed Ali Asad RizviZongli LinPublished in: CDC (2018)
Keyphrases
- model free
- linear systems
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- sufficient conditions
- dynamical systems
- temporal difference
- policy iteration
- state space
- sparse linear systems
- markov chain
- control system
- reinforcement learning methods
- mathematical model
- policy evaluation
- learning algorithm
- average reward
- rl algorithms
- coefficient matrix
- markov decision processes
- learning problems
- finite state
- optimal policy
- learning process
- temporal difference learning
- data mining