Thompson-Sampling Based Reinforcement Learning for Networked Control of Unknown Linear Systems.
Borna SayedanaMohammad AfshariPeter E. CainesAditya MahajanPublished in: CDC (2022)
Keyphrases
- linear systems
- control theory
- reinforcement learning
- dynamical systems
- sufficient conditions
- control problems
- linear equations
- sparse linear systems
- optimal control
- monte carlo
- control policy
- machine learning
- coefficient matrix
- control system
- interior point methods
- dynamic model
- control method
- function approximation
- control strategy
- markov decision processes
- state space
- expert systems
- learning algorithm