research
∙
06/19/2022
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Myopic exploration policies such as epsilon-greedy, softmax, or Gaussian...
share
research
∙
04/17/2018
Two-Player Games for Efficient Non-Convex Constrained Optimization
In recent years, constrained optimization has become increasingly releva...
research
∙
11/09/2017
Small-loss bounds for online learning with partial information
We consider the problem of adversarial (non-stochastic) online learning ...
research
∙
02/21/2015
