Reinforcement Learning-based Decentralized Optimal Control for Large-Scale Multi-agent System by Using Neural Networks and Discrete-time Mean Field Games.
Zejian ZhouYuzhu ZhangHao XuPublished in: IJCNN (2021)
Keyphrases
- optimal control
- reinforcement learning
- optimal control problems
- neural network
- multi agent
- multi agent systems
- cooperative
- control problems
- linear quadratic
- game theory
- dynamic programming
- feedback control
- learning agents
- markov random field
- control strategy
- function approximation
- actor critic
- multiagent systems
- function approximators
- class of nonlinear systems
- infinite horizon
- control law
- state space
- single agent
- markov processes
- rl algorithms
- lyapunov function
- reinforcement learning algorithms
- temporal difference
- model free
- finite state
- approximate dynamic programming
- optimal policy
- real time