Learning to Communicate Using Action Probabilities for Multi-Agent Cooperation.
Yidong BaiToshiharu SugawaraPublished in: ICA (2023)
Keyphrases
- learning algorithm
- reinforcement learning
- learning process
- prior knowledge
- online learning
- incremental learning
- learning systems
- artificial intelligence
- probability distribution
- learning from experience
- database
- action models
- action sequences
- share information
- inductive inference
- learning problems
- mobile learning
- empirical studies
- active learning
- knowledge base
- social networks
- machine learning
- neural network