Olivier Delalleau's repositories
NeMo
NeMo: a toolkit for conversational AI
omegaconf
Flexible Python configuration system. The last one you will ever need.
hydra
Hydra is a framework for elegantly configuring complex applications
NeMo-Megatron-Launcher
NeMo Megatron launcher and tools
CORL
High-quality single-file implementations of SOTA Offline RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC
mtenv
MultiTask Environments for Reinforcement Learning.
mbrl-lib
Library for Model Based RL
minihack
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
mvfst
An implementation of the QUIC transport protocol.
folly
An open-source C++ library developed and used at Facebook.
verus
Verus is an adaptive congestion control protocol that is custom designed for cellular networks.
genericCC
An interface to program any congestion control protocol for an unreliable connection based protocol sent over UDP. It comes with a clean TrafficGenerator interface that can generate traffic for each of these various protocols. Also supports other congestion control protocols
pantheon-tunnel
Instrumented tunnel for measuring congestion control schemes in either direction
active-mri-acquisition
Active Acquisition for fastMRI
pycolab
A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!
keras-rl
Deep Reinforcement Learning for Keras.
RL-Adventure
Pytorch easy-to-follow step-by-step Deep Q Learning tutorial with clean readable code.
FractalAI
Cellular automaton-based calculus for the masses
nuclai16
Support material for nucl.ai Conference 2016 workshops and open laboratories.
ViZDoom
Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information.
neural-doodle
Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there's more! (An implementation of Semantic Style Transfer.)
nucl.ai-vizdoom-workshop
nucl.ai 2016 Hands-On Deep Q-Learning in Doom Workshop
spark
Mirror of Apache Spark
SpelunkBots
An API that allows for AI bots to be written in the original 2009 version of Spelunky.