Tim Rocktäschel's Projects
impact-driven-exploration
Learning to Execute
Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:
Write PyTorch code at the level of individual examples, then run it efficiently on minibatches.
Memory Networks implementations
Utility library for functional programming in Lua
Tensorflow Implementation of Multi-Function Recurrent Unit
Neural Attention Model for Abstractive Summarization
Official NetHack Git Repository
The NetHack Learning Environment
org-babel integration with Jupyter for evaluation of (Python by default) code blocks
Face recognition with Google's FaceNet deep neural network.
Simple game library for Android
Traditional roguelike game with pixel-art graphics and simple interface
Traditional roguelike game with pixel-art graphics and simple interface - Remixed Pixel Dungeon
Tensorflow implementation of "The Predictron: End-To-End Learning and Planning"
A video game description language (VGDL) built on top pf pygame.
A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Minicourse in Deep Learning with PyTorch
Simple examples to introduce PyTorch
PyTorch Tutorial for Deep Learning Researchers
A small package to create visualizations of PyTorch execution graphs
Question answering dataset featured in "Teaching Machines to Read and Comprehend
Retro Games in Gym