• Publications
  • Influence
Finite-time Analysis of the Multiarmed Bandit Problem
We show that the optimal logarithmic regret is also achievable uniformly over time, with simple and efficient policies, and for all reward distributions with bounded support. Expand
  • 4,339
  • 969
  • PDF
Proceedings of the Thirteenth Annual Conference on Computational Learning Theory (COLT 2000), June 28 - July 1, 2000, Palo Alto, California, USA
Proceedings of the Annual Workshops on Computational Learning Theory, available for 1988-2000. Expand
  • 2
Algorithmic Learning Theory
The 15th International Conference on Algorithmic Learning Theory (ALT’04) and the 7th International conference on Discovery Science will be held at Padova University, Padova, Italy, October 2 5, 2004 as part of the Padova Dialogues. Expand
  • 2
Online learning for CAT applications