Repositories (24)
TensorFlow-based neural network library
StarCraft II Learning Environment
A customisable 3D platform for agent-based AI research
Build Graph Nets in Tensorflow
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Learning to Learn in TensorFlow
JAX-based neural network library
Optax is a gradient processing and optimization library for JAX.
Tracking Any Point (TAP)
A JAX research toolkit for building, editing, and visualizing neural networks.
A Graph Neural Network Library in Jax
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
An interactive HTML pretty-printer for machine learning research in IPython notebooks.
PIX is an image processing library in JAX, for JAX.
A customisable 2D platform for agent-based AI research
Spriteworld: a flexible, configurable python-based reinforcement learning environment
Second Order Optimization and Curvature Estimation with K-FAC in JAX.
A Python interface for reinforcement learning environments
Benchmarking physical understanding in generative video models
A tool for recording RL trajectories.
NEVIS'22: Benchmarking the next generation of never-ending learners
ML-guided enzyme engineering
This repository contains the code of the distribution shift framework presented in A Fine-Grained Analysis on Distribution Shift (Wiles et al., 2022).