451 citations · 1.7k across the 73 of their papers we have counts for
Showing 2017 · stat.MLShow all
3 papers · 2 filters
stat.ML2017★ 9 cited
On Optimistic versus Randomized Exploration in Reinforcement Learning
Ian Osband, Benjamin Van Roy
We discuss the relative merits of optimistic and randomized approaches to exploration in reinforcement learning. Optimistic approaches presented in the literature apply an optimist…
stat.ML2017★ 46 cited
Ensemble Sampling
Xiuyuan Lu, Benjamin Van Roy
Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems. In its basic form, the algorithm requires computing and sampling from a poste…
stat.ML2017★ 1 cited
Gaussian-Dirichlet Posterior Dominance in Sequential Learning
Ian Osband, Benjamin Van Roy
We consider the problem of sequential learning from categorical observations bounded in [0,1]. We establish an ordering between the Dirichlet posterior over categorical outcomes an…