Search Results for author:
Found 3 papers, 0 papers with code
Scale Free Adversarial Multi Armed Bandits
This technique plays a crucial role in our analysis for controlling the regret when using importance weighted estimators of unbounded losses.
Exponential Weights on the Hypercube in Polynomial Time
This problem is equivalent to OLO on the $\{0, 1\}^n$ hypercube.
Efficient Reinforcement Learning via Initial Pure Exploration
Based of the scores she obtains in these practice tests, she would formulate a strategy for maximizing her scores in the actual tests.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
