A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems.
Mukul GagraniSagar SudhakaraAditya MahajanAshutosh NayyarYi OuyangPublished in: CoRR (2021)
Keyphrases
- linear systems
- control theory
- reinforcement learning
- sufficient conditions
- optimal control
- control system
- dynamical systems
- linear equations
- control strategy
- probability distribution
- coefficient matrix
- learning algorithm
- knn
- state space
- control policy
- control method
- control scheme
- pid controller
- dynamic programming
- decision making
- real time