Q-learning algorithm in solving consensusability problem of discrete-time multi-agent systems.
Tao FengJilie ZhangYin TongHuaguang ZhangPublished in: Autom. (2021)
Keyphrases
- multi agent systems
- learning algorithm
- semi markov decision processes
- machine learning
- machine learning algorithms
- multi agent
- training data
- reinforcement learning
- active learning
- complex systems
- autonomous agents
- agent systems
- coalition formation
- game theory
- generalization ability
- learning rate
- neural network
- learning scheme
- rbf network
- agent technology
- agent architecture
- steady state
- dynamic environments
- markov chain
- lower bound
- cooperative