Fast and reliable distributed systems in Python

Building blocks for productive research

[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model

Large Concept Models: Language modeling in a sentence representation space

Imitation learning algorithms

Modern Robotics: Mechanics, Planning, and Control Code Library --- The primary purpose of the provided software is to be easy to read and educational, reinforcing the concepts in the book. The code…

Official PyTorch Implementation for Readout Guidance, CVPR 2024

Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

Embodied Chain of Thought: A robotic policy that reason to solve the task.

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

Connect agent policies for distributed ML applications

Official Implementation for the paper "SR-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models"

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

A Swiss Army knife for developers.

CLU lets you write beautiful training loops in JAX.

Personal schematic symbol and footprint libraries for Altium Designer.

Development repository for the Triton language and compiler

NGC-Lava: NGC-Learn Support for Loihi 2 Lava Spiking Networks

ICRA2024 Paper List

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Official implementation of paper "A neural active inference model of perceptual-motor learning" published on Computational Neuroscience in 2023.

Official Implementation for the paper Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking System.

NGC Museum: Biomimetic Credit Assignment and Brain-Inspired Computing with NGC-Learn

Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022

Agent Learning Framework https://alf.readthedocs.io

Load tensorboard event logs as pandas DataFrames for scientific plotting; Supports both PyTorch and TensorFlow

A quick example of how one can "synchronize" a 3d scene across multiple windows using three.js and localStorage

Code for reproducing experiments in Model-Based Active Exploration, ICML 2019