odalric-ambrym.maillard.over-blog.com
Optimal regret bounds for selecting the state representation in reinforcement learning. - Odalric-Ambrym Maillard
http://odalric-ambrym.maillard.over-blog.com/article-optimal-regret-bounds-for-selecting-the-state-representation-in-reinforcement-learning-115774394.html
Thanks to OverBlog Reader, follow this blog and don't miss any of its best posts! Optimal regret bounds for selecting the state representation in reinforcement learning. Odalric-Ambrym Maillard, Phuong Nguyen. Proceedings of the 30th international conference on machine learning, ICML 2013. You can dowload the paper from the ICML website. And a corrected version from the HAL online open depository. The correction is minor and changes only a constant 2 into 2 sqrt{2}). See also a talk. Year = "2013",.
odalric-ambrym.maillard.over-blog.com
Competing with an Infinite Set of Models in Reinforcement Learning - Odalric-Ambrym Maillard
http://odalric-ambrym.maillard.over-blog.com/article-competing-with-an-infinite-set-of-models-in-reinforcement-learning-116177253.html
Thanks to OverBlog Reader, follow this blog and don't miss any of its best posts! Optimal regret bounds for. Competing with an Infinite Set of Models in Reinforcement Learning. Odalric-Ambrym Maillard, Daniil Ryabko. International Conference on Artificial Intelligence and Statistics. You can dowload the paper from the JMLR website. Or from the HAL online open depository. Optimal regret bounds for selecting the state representation in reinforcement learning. Odalric-Ambrym Maillard, Phuong Nguyen. Concent...
hal.archives-ouvertes.fr
The Replacement Bootstrap for Dependent Data
https://hal.archives-ouvertes.fr/hal-01144547
Have you forgotten your login? Your account and profile. Why you should create your account and profile on HAL. How to create your account or profile in HAL. Modifying your account or profile on HAL. In case of forgotten login or password. Types of publications accepted on HAL. How to upload files. Document description : common metadata. Document description : specific metadata sorted by publication type order. Recap and how to link several deposits. How to retrieve the metadata from the PDF file. Requir...
odalric-ambrym.maillard.over-blog.com
discussing articles - Odalric-Ambrym Maillard
http://odalric-ambrym.maillard.over-blog.com/tag/discussing%20articles
Thanks to OverBlog Reader, follow this blog and don't miss any of its best posts! Concentration inequalities for sampling without replacement. Bernoulli Journal, 2014. You can dowload the paper from the Bernoulli website. Here) or from the HAL online open depository. The HAL open-access online archive system seeks to make research results available to the widest audience, independently of the major publisher,. And cooperates with other large international archives like arXiv. We study a variant of the st...
spice.lif.univ-mrs.fr
SPiCe: Sequence PredIction ChallengE
http://spice.lif.univ-mrs.fr/committee.php
Lancaster University, United Kingdom. Marc G. Bellemare. Google DeepMind, United Kingdom. Xerox Research Center Europe. King's College London, United Kingdom. Aix-Marseille Université, France. Aix-Marseille Université, France. Colin de la Higuera. University of Nantes, France. Universidad Nacional de Córdoba and CONICET, Argentina. Xerox Research Center Europe. INRIA Lille, France. University of Leicester, United Kingdom. Delft University of Technology, The Netherlands. Tilburg University,The Netherlands.
odalric-ambrym.maillard.over-blog.com
Events - Odalric-Ambrym Maillard
http://odalric-ambrym.maillard.over-blog.com/pages/Events-1843227.html
Thanks to OverBlog Reader, follow this blog and don't miss any of its best posts! Some interesting events I have participated in/attended:. September, 15-19, 2014, Nancy (France): European conference on Machine Learning. June, 21-26 , 2014, Beijing(China): 31st International Conference on Machine Learning. June, 01, 2014, Haifa (Israel):. I am now an official Senior Researcher at the Technion. April,13 - May 25, 2014, Lille (France). Visit at INRIA Lille. February, 2014, Haifa. 10-22, 2014, Toulouse (.
odalric-ambrym.maillard.over-blog.com
Publications - Odalric-Ambrym Maillard
http://odalric-ambrym.maillard.over-blog.com/pages/Publications-1843191.html
Thanks to OverBlog Reader, follow this blog and don't miss any of its best posts! Here are some of my contributions. Other papers are under review, others are in progress. Selecting Near-Optimal Approximate State Representations in Reinforcement Learning. Odalric-Ambrym Maillard, Daniil Ryabko. Sub-sampling for multi-armed bandits. Akram Baransi, Odalric-Ambrym Maillard, Shie Mannor. Europeean conference on Machine Learning, 2014. Concentration inequalities for sampling without replacement. Proceedings o...
odalricambrymmaillard.wordpress.com
Competing with an Infinite Set of Models in Reinforcement Learning. – Odalric-Ambrym Maillard
https://odalricambrymmaillard.wordpress.com/2014/08/09/competing-with-an-infinite-set-of-models-in-reinforcement-learning
My research journey in Mathematics and Computer Science. How hard is my MDP? Distribution-norm to the rescue. Selecting Near-Optimal Approximate State Representations in Reinforcement Learning. Sub-sampling for multi-armed bandits. Concentration inequalities for sampling without replacement. Robust Risk-averse Multi-armed Bandits. Competing with an Infinite Set of Models in Reinforcement Learning. Optimal regret bounds for selecting the state representation in reinforcement learning. Or from the HAL onli...
odalricambrymmaillard.wordpress.com
Selecting the State-Representation in Reinforcement Learning. – Odalric-Ambrym Maillard
https://odalricambrymmaillard.wordpress.com/2014/08/05/selecting-the-state-representation-in-reinforcement-learning
My research journey in Mathematics and Computer Science. How hard is my MDP? Distribution-norm to the rescue. Selecting Near-Optimal Approximate State Representations in Reinforcement Learning. Sub-sampling for multi-armed bandits. Concentration inequalities for sampling without replacement. Robust Risk-averse Multi-armed Bandits. Competing with an Infinite Set of Models in Reinforcement Learning. Optimal regret bounds for selecting the state representation in reinforcement learning. You can dowload the ...