Search

Odalric-Ambrym Maillard

Towards instance-dependent regret optimality in Episodic MDPs with Posterior Sampling
Fast asymptotically optimal algorithms for non-parametric stochastic bandits
From Optimality to Robustness: Adaptive Re-Sampling Strategies in Stochastic Bandits
Optimal Thompson Sampling strategies for support-aware CVaR bandits
Sub-sampling for Efficient Non-Parametric Bandit Exploration

Published with Wowchemy — the free, open source website builder that empowers creators.