Scalable toolkit for efficient model alignment

TensorDict is a pytorch dedicated tensor container.

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

GPU implementation of a fast generalized ANS (asymmetric numeral system) entropy encoder and decoder, with extensions for lossless compression of numerical and other data types in HPC/ML applications.

A library for differentiable nonlinear optimization

Dora is an experiment management framework. It expresses grid searches as pure python files as part of your repo. It identifies experiments with a unique hash signature. Scale up to hundreds of exp…

MultiTask Environments for Reinforcement Learning.

Multi Task RL Baselines

Library for Model Based RL

API for accessing the GraphLog dataset

Model interpretability and understanding for PyTorch

Active Acquisition for fastMRI

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Notes and exercise solutions for second edition of Sutton & Barto's book

Summaries for exciting works in the field of Deep Learning.

Modeling agents with probabilistic programs

RLgraph: Modular computation graphs for deep reinforcement learning

Advanced Differentiable Neural Computer (ADNC) with application to bAbI task and CNN RC task.

A set of Lecture notes for teaching Reinforcement Learning

Miscellaneous Python utilities

Leon stuff

Backup of PLearn

Git pre-commits hooks for doing Python code formatting checks

Git pre-commits hooks for doing Python code formatting checks

Deep Learning Tutorial notes and code. See the wiki for more info.

My own fork of Theano

My own fork of Pylearn

Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.…

Warning: This project does not have any current developer. See bellow.