Multi-agent cooperation Q-learning algorithm based on constrained Markov Game.
Yangyang GeFei ZhuWei HuangPeiyao ZhaoQuan LiuPublished in: Comput. Sci. Inf. Syst. (2020)
Keyphrases
- multi agent cooperation
- game theory
- learning algorithm
- multi agent systems
- game theoretic
- multi agent
- nash equilibrium
- cooperative
- markov chain
- computer games
- nash equilibria
- machine learning algorithms
- training data
- reinforcement learning
- active learning
- markov model
- game playing
- machine learning
- cooperative problem solving
- supervised learning
- learning tasks
- conditional independence
- learning scheme
- serious games
- game play
- virtual world
- learning rate
- generalization error
- neural network
- learning problems
- classification algorithm
- educational games
- learning process
- video games
- online game
- back propagation
- imperfect information
- learning games
- semi markov
- cooperative game
- training examples
- training samples