A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Video datasets

Large World Model -- Modeling Text and Video with Millions Context

(Crafter + NetHack) in JAX. ICML 2024 Spotlight.

Python scripting for Godot. This GDExtension plugin allows you to use Python like GDScript, accessing the Godot engine's features and benefiting from Python's vast ecosystem.

🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL

Official code for Goldfish model for long video understanding and MiniGPT4-video for short video understanding

Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities (NeurIPS 2023)

109,110 news from Reuters.

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically ground…

Multi Robot Systems gym environment based on Pybullet

Official Pytorch implementation of "Graphit: A Unified Framework for Diverse Image Editing Tasks"

Constrained optimization toolkit for PyTorch

Convert Machine Learning Code Between Frameworks

Deep reinforcement learning framework for fast prototyping based on PyTorch

PyTorch implementation of normalizing flow models

[NeurIPS 2019] Deep Set Prediction Networks

A latent text-to-image diffusion model

A small package to create visualizations of PyTorch execution graphs

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set …

This is a minimal example to demonstrate how multi-agent reinforcement learning with differentiable communication channels and centralized critics can be realized in RLLib. This example serves as a…

Turning SymPy expressions into PyTorch modules.

A differentiable argmax function for PyTorch

gradslam is an open source differentiable dense SLAM library for PyTorch

Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

Python ROS depth estimation from RGB image based on code from the paper "High Quality Monocular Depth Estimation via Transfer Learning"

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

A library for efficient similarity search and clustering of dense vectors.

Samples and bindings for the Google Assistant API