Learning Superior Cooperative Policy in Adversarial Multi-Team Reinforcement Learning.
Qingxu FuTenghai QiuZhiqiang PuJianqiang YiXiaolin AiWanmai YuanPublished in: IJCNN (2023)
Keyphrases
- reinforcement learning
- cooperative
- learning process
- multi agent
- learning algorithm
- function approximation
- learning tasks
- learning systems
- optimal policy
- solve complex tasks
- partially observable environments
- cooperating agents
- action selection
- neural network
- online learning
- dynamic programming
- bayesian networks
- learning problems
- model free
- supervised learning
- temporal difference
- policy search
- machine learning