• 2
• 0
• 0

loopix-messaging

Anonymous messaging using mix networks

• 2
• 0
• 0

gqn-datasets

Datasets used to train Generative Query Networks (GQNs) in the ‘Neural Scene Representation and Rendering’ paper.

• 2
• 0
• 0

ai-safety-gridworlds

This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.

• 2
• 0
• 0

pysc2

StarCraft II Learning Environment

• 2
• 0
• 0

dsprites-dataset

Dataset to assess the disentanglement properties of unsupervised learning methods

• 2
• 0
• 0

mnist-cluttered

Cluttered MNIST Dataset

• 2
• 0
• 0

learning-to-learn

Learning to Learn in TensorFlow

• 2
• 0
• 0

card2code

A code generation dataset for generating the code that implements Hearthstone and Magic The Gathering card effects.

• 2
• 0
• 0

torch-totem

Torch test module

• 2
• 0
• 0

torch-dokx

Scripts to help with Torch package documentation

• 2
• 0
• 0

torch-oocairo

Cairo lua bindings with extensions for torch

• 3
• 1
• 0

tapnet

Tracking Any Point (TAP)

• 3
• 0
• 0

perception_test

• 3
• 0
• 0

zipfian_environments

• 3
• 0
• 0

alphatensor

• 3
• 0
• 0

tell_me_why_explanations_rl

• 3
• 0
• 0

disdain

A self-contained JAX implementation of DIScriminator DisAgreement INtrinsic Reward (DISDAIN).

• 3
• 0
• 0

agent_debugger

Causal Analysis of Agent Behavior for AI Safety

• 3
• 0
• 0

jax_privacy

Algorithms for Privacy-Preserving Machine Learning in JAX

• 3
• 0
• 0

flows_for_atomic_solids