Optimal Consensus Control for Continuous-time Multi-agent Systems via Actor-Critic Neural Networks.
Xiao JiaKatinka WolterPublished in: ICARA (2022)
Keyphrases
- optimal control
- actor critic
- neural network
- multi agent systems
- control problems
- dynamic programming
- control strategy
- policy gradient
- approximate dynamic programming
- infinite horizon
- reinforcement learning
- fuzzy logic
- control system
- control policy
- control law
- artificial neural networks
- monte carlo
- feed forward
- dynamic environments
- control method
- state space
- average cost
- average reward
- optimal solution
- multi agent