Hugo Caselles-Dupré's repositories
NeurIPS19-SBDRL
Code for NeurIPS 2019 paper: "Symmetry-Based Disentangled Representation Learning requires Interaction with Environments" by H. Caselles-Dupré, M. Garcia-Ortiz and D. Filliat.
graph_kernels
Four of the main kernels on graphs Python implementation.
paper_notes
Paper notes for my PhD on Machine Learning (mostly focused on Reinforcement Learning)
Deep_Q-Network
Implementation of DeepMind's Deep Q-Network for Reinforcement Learning on OpenAI Gym, using Python with Keras.
classic_classifiers
Comparison of 5 predictive algorithms on a imbalanced 0-1 dataset.
Compressed_sensing_astronomy
Compressed sensing applied to Astronomy
Entropic_Affinities
A sparsification method for graph-based clustering and semi-supervised learning tasks, implemented on Python.
Automatic_estimation_poses_3D
Automatic estimation of 3D human poses from videos.
caselles.github.io
PhD website
Double-DQN_theano_only
Project for ENSAE's ELTDM course : implementation of Deep Q-Network using only Theano.
NeurIPS22-demonstrations-pedagogy-pragmatism
A repository containing the code for NeurIPS22 paper "Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments"