Distributed consensus for nonlinear multi-agent systems with two-time-scales: A hybrid reinforcement learning consensus algorithm.
Chuanjun PengJianwei XiaJing WangHao ShenPublished in: Inf. Sci. (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- multi agent systems
- np hard
- linear programming
- dynamic programming
- significant improvement
- k means
- cost function
- recognition algorithm
- detection algorithm
- worst case
- computational complexity
- optimal solution
- distributed systems
- multi agent
- simulated annealing
- single agent
- optimization algorithm
- search space
- computational cost
- distributed environment
- neural network
- cooperative
- function approximators