Pure Exploration

Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs
In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to identify an $\epsilon$-optimal policy with …
Andrea Tirinzoni, Aymen Al Marjani, Emilie Kaufmann
Cite PDF Slides Arxiv
On the complexity of All ε-Best Arms Identification
We consider the question introduced by \cite{Mason2020} of identifying all the $\varepsilon$-optimal arms in a finite stochastic …
Aymen Al Marjani, Tomáš Kocák, Aurélien Garivier
Cite PDF Arxiv
Navigating to the Best Policy in Markov Decision Processes
We investigate the classical active pure exploration problem in Markov Decision Processes, where the agent sequentially selects actions …
Aymen Al Marjani, Aurélien Garivier, Alexandre Proutiere
Cite PDF Slides Video Arxiv
Adaptive Sampling for Best Policy Identification in Markov Decision Processes
We investigate the problem of best-policy identification in discounted Markov Decision Processes (MDPs) when the learner has access to …
Aymen Al Marjani, Alexandre Proutiere
Cite PDF Slides Arxiv