Search Results for author:
Found 3 papers, 2 papers with code
Meta-Learning for Simple Regret Minimization
The Bayesian algorithm has access to a prior distribution over the meta-parameters and its meta simple regret over $m$ bandit tasks with horizon $n$ is mere $\tilde{O}(m / \sqrt{n})$.
Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms
We study a sequential decision problem where the learner faces a sequence of $K$-armed bandit tasks.
Guaranteed Fixed-Confidence Best Arm Identification in Multi-Armed Bandits: Simple Sequential Elimination Algorithms
We propose to use the classical "vector at a time" (VT) rule, which samples each remaining arm once in each round.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
