Pinned Repositories
ComputationalStatistics_Class
A theoretical and numerical tour of computational statistics
cppn
A pytorch implementation of what is described by hardmaru: http://blog.otoro.net/2016/04/01/generating-large-images-from-latent-vectors/
Cycle-GAN-for-euclidian-spaces
A cycle gan model to handle euclidian-like distribution
fabienpesquerel.github.io
forban
A simple environment to test and benchmark algorithms tackling various bandit problems.
IMED-RL
Source code for the paper "IMED-RL: Regret optimal learning of ergodic Markov decision processes" - NeurIPS 2022
Logarithmic-regret-in-communicating-MDPs-Leveraging-known-dynamics-with-bandits
Code for NeurIPS 2023. We study regret minimization in an average-reward and communicating Markov Decision Process (MDP) with known dynamics, but unknown reward function.
MCMC
Python implementation (from scratch) of some MCMC samplers that can leverage pyTorch's autodifferentiation (with examples).
ReinforcementLearning_Class
A theoretical and numerical tour of Reinforcement Learning (and sequential decision making)
stochastic-bandits-with-groups-of-similar-arms-neurips-2021
This is the official repository of the paper Stocastic bandits with groups of similar arms (NeurIPS 2021). It contains the code that was used to compute the figures and experiments of the paper.
fabienpesquerel's Repositories
fabienpesquerel/cppn
A pytorch implementation of what is described by hardmaru: http://blog.otoro.net/2016/04/01/generating-large-images-from-latent-vectors/
fabienpesquerel/MCMC
Python implementation (from scratch) of some MCMC samplers that can leverage pyTorch's autodifferentiation (with examples).
fabienpesquerel/forban
A simple environment to test and benchmark algorithms tackling various bandit problems.
fabienpesquerel/IMED-RL
Source code for the paper "IMED-RL: Regret optimal learning of ergodic Markov decision processes" - NeurIPS 2022
fabienpesquerel/ComputationalStatistics_Class
A theoretical and numerical tour of computational statistics
fabienpesquerel/Cycle-GAN-for-euclidian-spaces
A cycle gan model to handle euclidian-like distribution
fabienpesquerel/fabienpesquerel.github.io
fabienpesquerel/Logarithmic-regret-in-communicating-MDPs-Leveraging-known-dynamics-with-bandits
Code for NeurIPS 2023. We study regret minimization in an average-reward and communicating Markov Decision Process (MDP) with known dynamics, but unknown reward function.
fabienpesquerel/ReinforcementLearning_Class
A theoretical and numerical tour of Reinforcement Learning (and sequential decision making)
fabienpesquerel/stochastic-bandits-with-groups-of-similar-arms-neurips-2021
This is the official repository of the paper Stocastic bandits with groups of similar arms (NeurIPS 2021). It contains the code that was used to compute the figures and experiments of the paper.
fabienpesquerel/tda_project
fabienpesquerel/thesis
Repository for my PhD manuscript