Contextual Bandits with Cross-Learning
Santiago Balseiro, Negin Golrezaei, Mohammad Mahdian, Vahab Mirrokni, Jon Schneider
–Neural Information Processing Systems
In the classical contextual bandits problem, in each roundt, a learner observes some contextc, chooses some actiona to perform, and receives some reward ra,t(c).
Neural Information Processing Systems
Feb-12-2026, 11:56:36 GMT
- Country:
- Technology:
- Information Technology
- Artificial Intelligence > Machine Learning (0.48)
- Data Science > Data Mining
- Big Data (0.77)
- Game Theory (0.48)
- Information Technology