Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communication.
William ChangYuanhao LuPublished in: CoRR (2023)
Keyphrases
- cooperative
- reinforcement learning
- multi armed bandits
- learning process
- knowledge acquisition
- learning analytics
- learning algorithm
- learning scenarios
- information sharing
- dynamic programming
- active learning
- machine learning
- online learning
- supervised learning
- unsupervised learning
- learning tasks
- prior knowledge
- serious games