Hierarchical Optimal Synchronization for Linear Systems via Reinforcement Learning: A Stackelberg-Nash Game Perspective.
Man LiJiahu QinQichao MaWei Xing ZhengYu KangPublished in: IEEE Trans. Neural Networks Learn. Syst. (2021)
Keyphrases
- linear systems
- nash equilibrium
- game theory
- nash equilibria
- reinforcement learning
- game theoretic
- stackelberg game
- optimal strategy
- sufficient conditions
- dynamical systems
- dynamic programming
- stochastic games
- optimal solution
- worst case
- sparse linear systems
- incomplete information
- multi agent
- mixed strategy
- leader follower
- multi agent systems
- markov decision processes
- utility function
- resource allocation
- genetic algorithm
- coefficient matrix
- np hard