A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).

Trains Transformer model variants. Data isn't shuffled between batches.

End-to-End Object Detection with Transformers

Neural Text Generation with Unlikelihood Training

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Transformer training code for sequential tasks

StarCraft: BroodWars OpenAI Gym environment

Gym - Doom environments based on VizDoom.

PyTorch implementation of CommNet

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKT…

PyTorch implementation of Trust Region Policy Optimization

Implementation of TRPO and related algorithms

[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

A toolkit for developing and comparing reinforcement learning algorithms.

Minimal and Clean Reinforcement Learning Examples

Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy https://visdom.dev

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Python bindings for pyNVML and psutil library over network

A list of resources for all invited talks, tutorials, workshops and presentations at NIPS 2016

Modular multitask reinforcement learning with policy sketches

Neural network model, suitable for multi-agent learning. https://arxiv.org/abs/1605.07736

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

A dependency free, embeddable debugger for Lua in a single file (.lua or .h)

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

Library for fast text representation and classification.

Keras code and weights files for popular deep learning models.