Optimal Consensus Control for Discrete-Time Systems with State Delay Using Q-learning Solution.
Li ZhangShicheng HuoYa ZhangPublished in: ICCA (2022)
Keyphrases
- control policy
- reinforcement learning
- state space
- optimal solution
- dynamic programming
- closed form
- neural network
- optimal control
- state information
- control system
- markov chain
- learning algorithm
- control method
- sufficient conditions
- cooperative
- complex systems
- finite state
- model free
- linear systems
- control theory
- lower bound
- locally optimal
- traffic signal
- optimal control problems