Correcting biased value estimation in mixing value-based multi-agent reinforcement learning by multiple choice learning.
Bing LiuYuxuan XieLei FengPing FuPublished in: Eng. Appl. Artif. Intell. (2022)
Keyphrases
- multi agent reinforcement learning
- multiple choice
- reinforcement learning
- open ended
- learning agents
- active learning
- learning algorithm
- learning tasks
- machine learning
- knowledge acquisition
- cooperative learning
- learning mechanism
- learning capabilities
- learning environment
- stochastic games
- artificial intelligence
- multi agent learning