Safe Q-learning for continuous-time linear systems.
Soutrik BandyopadhyayShubhendu BhasinPublished in: CoRR (2023)
Keyphrases
- linear systems
- dynamical systems
- state space
- reinforcement learning
- sufficient conditions
- control theory
- function approximation
- linear equations
- learning algorithm
- coefficient matrix
- markov chain
- differential equations
- multi agent
- optimal control
- optimal policy
- sparse linear systems
- model free
- markov decision processes
- basis functions
- artificial neural networks
- dynamic programming
- search space