Maximum Correntropy Value Decomposition for Multi-agent Deep Reinforcemen Learning.
Kai LiuTianxian ZhangLingjiang KongPublished in: CoRR (2022)
Keyphrases
- multi agent
- reinforcement learning
- learning algorithm
- learning process
- real time
- learning problems
- learning agents
- prior knowledge
- online learning
- learning systems
- learning tasks
- supervised learning
- elementary school
- learning scheme
- incremental learning
- unsupervised learning
- probabilistic model
- active learning
- mobile devices
- machine learning