Safe Q-Learning for Continuous-Time Linear Systems.
Soutrik BandyopadhyayShubhendu BhasinPublished in: CDC (2023)
Keyphrases
- linear systems
- dynamical systems
- state space
- reinforcement learning
- sufficient conditions
- function approximation
- coefficient matrix
- linear equations
- markov chain
- multi agent
- control theory
- learning algorithm
- differential equations
- optimal policy
- model free
- sparse linear systems
- optimal control
- action selection
- pid controller
- markov decision processes
- interior point methods
- genetic algorithm