51. Dsprites Dataset
Dataset to assess the disentanglement properties of unsupervised learning methods
52. Spriteworld
Spriteworld: a flexible, configurable python-based reinforcement learning environment
53. Lab2d
A customisable 2D platform for agent-based AI research
56. Spiral
We provide a pre-trained model for unconditional 19-step generation of CelebA-HQ images
✭ 293
58. Gqn Datasets
Datasets used to train Generative Query Networks (GQNs) in the ‘Neural Scene Representation and Rendering’ paper.
✭ 256
python61. card2code
A code generation dataset for generating the code that implements Hearthstone and Magic The Gathering card effects.
✭ 225
62. strict
A Lua package to detect reading of undeclared variables and creating of global variables.
✭ 21
lua64. dm robotics
Libraries, tools and tasks created and used at DeepMind Robotics.
68. android env
A library for doing RL research on Android devices.
71. pysc2
StarCraft II Learning Environment
73. mujoco
Multi-Joint dynamics with Contact. A general purpose physics simulator.
74. abstract-reasoning-matrices
Progressive matrices dataset, as described in: Measuring abstract reasoning in neural networks (Barrett*, Hill*, Santoro*, Morcos, Lillicrap), ICML2018
✭ 151
75. dm pix
PIX is an image processing library in JAX, for JAX.
80. boxoban-levels
This repository contains levels for boxoban, a box-pushing puzzle game inspired by Sokoban.
✭ 49
83. logical-entailment-dataset
This repository contains an entailment dataset for propositional logic, and code for generating that dataset. It also contains code for parsing the dataset in python.
84. interval-bound-propagation
This repository contains a simple implementation of Interval Bound Propagation (IBP) using TensorFlow: https://arxiv.org/abs/1810.12715
✭ 132
python85. labmaze
A standalone release of DeepMind Lab's maze generator with Python bindings.
89. envlogger
A tool for recording RL trajectories.
51-90 of 90 user projects