Chelsea Finn

maml. Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

maml_rl. Code for RL experiments in "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

gps. Guided Policy Search

rllab. rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

models. Models built with TensorFlow

caffe. Caffe: a Fast framework for deep learning. For the most recent version checkout the dev branch. For the latest stable release checkout the master branch.

bair_camp. Jupyter Notebook

nips17-dl-workshop-website. Website of the NIPS 2017 workshop: "Deep Learning: Bridging Theory and Practice"

PyGame-Learning-Environment. PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.

gym. A toolkit for developing and comparing reinforcement learning algorithms.

baselines. OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

pixel-cnn. Python3 / Tensorflow implementation of PixelCNN++, as described in "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"

bulletsim. Simulation environment with Bullet physics

ntm-one-shot. One-shot Learning with Memory-Augmented Neural Networks

Recipes. Lasagne recipes: examples, IPython notebooks, ...

gym-ple. This package allows to use PLE as a gym environment.

metaworld. An open source robotics benchmark for meta- and multi-task reinforcement learning

rutabaga. Python

gtsrb.torch. Traffic sign recognition with Torch

cs280report. Final Project Report for CS280

dotfiles. bash, zsh, git, tmux, personal toolbox

Lasagne. Lightweight library to build and train neural networks in Theano

ray. An experimental distributed execution engine