Automatically close issues that have a label, after a custom delay, if no one replies back.

robomimic: A Modular Framework for Robot Learning from Demonstration

[CVPR 2025 Oral] TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

A polyvalent C++ FEM library

CUDA on non-NVIDIA GPUs

🤖 The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation

Learn fundamental knowledge in robotics

Various retargeting optimizers to translate human hand motion to robot hand motion.

Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.

Incremental Potential Contact (IPC) is for robust and accurate time stepping of nonlinear elastodynamics. IPC guarantees intersection- and inversion-free trajectories regardless of materials, time-…

Build and run containers leveraging NVIDIA GPUs

A comment system powered by GitHub Discussions. 💬 💎

The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization

LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Train transformer language models with reinforcement learning.

Clean PyTorch implementations of imitation and reward learning algorithms

SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

Demo-Driven Mobile Bi-Manual Manipulation Benchmark.

Toolbox for our GraspNet-1Billion dataset.

My implementation of Graspnet Graspness.

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

📘 Automatic documentation from sources, for MkDocs.

Simulator of vision-based tactile sensors.