TF-Agents is a library for Reinforcement Learning in TensorFlow

The DM Control Suite and Package is a tool for developing and testing reinforcement learning agents for the MuJoCo physics engine.

Deep Planning Network: Control from pixels by latent planning with learned dynamics

Stochastic Adversarial Video Prediction https://video-prediction.github.io/video_prediction

Probabilistic reasoning and statistical analysis in TensorFlow

Learned Perceptual Image Patch Similarity (LPIPS) metric. In CVPR, 2018.

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/

Models built with TensorFlow

A toolkit for developing and comparing reinforcement learning algorithms.

Lightweight library to build and train neural networks in Theano

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic …

Computation using data flow graphs for scalable machine learning

Caffe: a fast open framework for deep learning.

CUDA SciKit

Client code for Jasper voice computing platform

Trajectory Optimization

Rapprentice: software for teaching robots by example