A multi-agent flocking collaborative control method for stochastic dynamic environment via graph attention autoencoder based reinforcement learning.
Jian XiaoGuohui YuanZhuoran WangPublished in: Neurocomputing (2023)
Keyphrases
- dynamic environments
- control method
- reinforcement learning
- multi agent
- reinforcement learning agents
- adaptive control
- single agent
- control algorithm
- control system
- grey prediction
- control strategy
- autonomous agents
- mobile robot
- reinforcement learning algorithms
- fuzzy control
- path planning
- pid controller
- multi agent environments
- fuzzy controller
- changing environment
- markov decision processes
- fuzzy pid control
- neural network
- learning agent
- pid control
- multi agent systems
- control scheme
- function approximation
- real environment
- matlab simulink
- fuzzy pid
- multiple agents
- model free
- fuzzy logic
- state space
- dc dc converter