Скачать или смотреть RLVS 2021 - Day 2 - Stochastic Bandits

Speaker: Tor Lattimore
Chairman: Sébastien Gerchinovitz

Abstract. The bandit framework specializes the reinforcement learning setup by removing the (controlled) state. Bandits provide all the essential ingredients to study the exploration/exploitation dilemma, with many principles derived for bandits generalizing to the reinforcement learning setting. The simplification has the advantage that it permits a more complete understanding and practical algorithms. Furthermore, bandits are a good model for many applications.

I will introduce bandit problems and present the most well-known algorithms based on the principle of optimism in the face of uncertainty. There will be a live coding demo and discussions of the many extensions needed in practical applications.

---------------
Reinforcement Learning Virtual School (March and April 2021).
https://rl-vs.github.io/rlvs2021/

Organized by the Toulouse AI institute ANITI, with the support of IRT Saint Exupéry, ISAE-SUPAERO, LAAS-CNRS, Université Fédérale Toulouse Midi-Pyrénées.
https://aniti.univ-toulouse.fr
https://www.irt-saintexupery.com/
https://www.isae-supaero.fr
https://www.laas.fr/
https://www.univ-toulouse.fr/

Officially sponsored by DeepMind.
https://deepmind.com/

We also thank Institut de Mathématiques de Toulouse - Université Toulouse III - Paul Sabatier, Toulouse School of Economics - Université Toulouse I - Capitole.
https://www.math.univ-toulouse.fr/
https://www.univ-tlse3.fr/
https://www.tse-fr.eu/fr
https://www.ut-capitole.fr/

This virtual event took place in March and April 2021. It gathered 1500 registered participants from 43 different countries.