Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

An offline deep reinforcement learning library

🎓 Easily create a beautiful academic résumé or educational website using Hugo, GitHub, and Netlify

PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.

Deep Q-Learning Network in pytorch

Experiment to see if some tweaks to a normal TensorFlow CNN can be used to identify multi-label MNIST example and locate the position of numbers in a multi-label input.

Probabilistic Torch is library for deep generative models that extends PyTorch

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

A w"hacky" road-segmentation network

Assignments for CS294-112.

Lane Following Demo in the gym-duckietown Simulator

A more-involved example ROS submission to the AIDO LF1 Challenge, using the Duckietown Lane Following stack.

Self-driving car simulator for the Duckietown universe

Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification

Tensorflow based implementation of deep siamese LSTM network to capture video based place similarity using cnn embeddings