The Sample Complexity of Exploration in the Multi-Armed Bandit Problem (Special Topic on Learning Theory)
John N. Tsitsiklis and Shie Mannor

10 day statistics (2 downloads)
Average Time 30 mins, 45 secs
Average Speed 0.09kB/s
Best Time 30 mins, 17 secs
Best Speed 0.10kB/s
Worst Time 31 mins, 13 secs
Worst Speed 0.09kB/s

Send Feedback