.. image:: pystat.png
    :height: 20
    :alt: Statistique
    :target: http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/td_2a_notions.html#pour-un-profil-plutot-data-scientist

.. _l-ml2a-bandits:

Bandits
+++++++

*(à venir)*

*Lectures*

* `Modeles de bandit : une histoire bayésienne et fréquentiste <http://chercheurs.lille.inria.fr/ekaufman/Matapli_Kaufmann.pdf>`_
* `Bandit theory, part I <http://blogs.princeton.edu/imabandit/2016/05/11/bandit-theory-part-i/>`_
* `Bandit theory, part II <http://blogs.princeton.edu/imabandit/2016/05/13/bandit-theory-part-ii/>`_
* `Kernel-based methods for bandit convex optimization, part 1 <http://blogs.princeton.edu/imabandit/2016/08/06/kernel-based-methods-for-bandit-convex-optimization-part-1/>`_
* `Kernel-based methods for bandit convex optimization, part 2 <http://blogs.princeton.edu/imabandit/2016/08/09/kernel-based-methods-for-convex-bandits-part-2/>`_
* `Kernel-based methods for bandit convex optimization, part 3 <http://blogs.princeton.edu/imabandit/2016/08/10/kernel-based-methods-for-convex-bandits-part-3/>`_
* `Learning to Interact <http://hunch.net/~jl/interact.pdf>`_ (John Langford)
* `Batch Learning from Logged Bandit Feedback through Counterfactual Risk Minimization <http://www.jmlr.org/papers/volume16/swaminathan15a/swaminathan15a.pdf>`_
* `Stochastic Structured Prediction under Bandit Feedback <https://papers.nips.cc/paper/6134-stochastic-structured-prediction-under-bandit-feedback.pdf>`_
* `Thompson sampling with the online bootstrap <https://arxiv.org/abs/1410.4009>`_ (à lire)
* `Trial without Error: Towards Safe Reinforcement Learning via Human Intervention <https://arxiv.org/abs/1707.05173>`_
* `Corrupt Bandits for Preserving Local Privacy <https://arxiv.org/abs/1708.05033>`_
* `Multi-Player Bandits Revisited <https://arxiv.org/abs/1711.02317>`_
* `Learning the distribution with largest mean: two bandit frameworks <https://arxiv.org/abs/1702.00001>`_
* `Analyse de stratégies bayésiennes et fréquentistes pour l’allocation séquentielle de ressources <http://chercheurs.lille.inria.fr/ekaufman/TheseEmilie.pdf>`_ (thèse)

*Modules*

* `SMPyBandits <https://github.com/SMPyBandits/SMPyBandits>`_,
  `SMPyBandits, a Research Framework for Single and Multi-Players Multi-Arms Bandits Algorithms in Python <https://perso.crans.org/besson/articles/SMPyBandits__Long_Version__02-2018.pdf>`_