Reward Surface for visualizing RL rewards

Official reference implementation of our paper "On Oversquashing in Graph Neural Networks Through The Lens of Dynamical Systems" accepted at AAAI 2025

finite element analysis for continuum mechanics of solid bodies

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

Implementation of a list sweeper: instead of the cartesian product, sweep over the zipped list

Spatio-Spectral Graph Neural Networks (S²GNN)

Oscillatory State-Space Models

Unstructured Compressible Navier Stokes 3D code (UCNS3D)

GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.

Repository to create traveling waves integrate special information through time

This gym provides implementations of various PDEs for easy testing and comparison of data-driven and classical PDE control algorithms.

Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms

XLB: Accelerated Lattice Boltzmann (XLB) for Physics-based ML

A Python framework for accelerated simulation, data generation and spatial computing.

A differentiable PDE solving framework for machine learning

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

A generative world for general-purpose robotics & embodied AI learning.

Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space.

Movement Primitive Diffusion (MPD) is a diffusion-based imitation learning method for high-quality robotic motion generation that focuses on gentle manipulation of deformable objects.

Fancy Gym: Unifying interface for various RL benchmarks with support for Black Box approaches.

clusterduck is a hydra launcher plugin for running jobs in batches on a SLURM cluster. It is intended for small tasks on clusters where jobs have exclusive access to a node, such that submitting a …

Unified framework for robot learning built on NVIDIA Isaac Sim

A modular, flexible framework for developing performant algorithms in Reinforcement Learning.

Movement Primitives in PyTorch

Implementation of different remote message passing strategies in graph neural networks for mesh-based physical simulation.

Code for Bayes-Adaptive Deep Model-Based Policy Optimisation

Graph-based Motion Planning Networks

Towards Autoencoding Variational Inference for Aspect-based Opinion Summary

Robust Quadrotor Frame for Machine Learning and Control Research