🎮 Multiplatform Python library for 3Dconnexion SpaceMouse devices using raw HID.

official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning (NeurIPS 2023)

Official code release for CoRL'25 paper: VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning

CoRL 2025 TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models

Official implementation for pi0 steering via DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

Official implementation for DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

off-policy algorithm utilizing offline and online data

Connect agent policies for distributed ML applications

Standard Open Arm 100

Simulated experiments for "Real-Time Execution of Action Chunking Flow Policies".

Cartesian impedance controller with reference limiting for Franka Emika Robot

This is a new repo used for training UAV navigation (local path planning) policy using DRL methods.

A student project comparing reinforcement learning algorithms on a panda robotic arm. Implemented PPO and its safety version, PPO Lagrangian, taking into account costs such as avoiding obstacles. E…

Model predictive control python toolbox

Reinforcement Learning with Model Predictive Control

Let us control diffusion models!

🦾 A Dual-System VLA with System2 Thinking

Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.

Official implementation of "OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning"

A Benchmark for Evaluating Generalization for Robotic Manipulation

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Creates up to 4 virtual xbox 360 controllers and feeds them via one or more keyboards.

🛠「Watt Toolkit」是一个开源跨平台的多功能 Steam 工具箱。

[NeurIPS 2025]⭐️ Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning.

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…

Educational Python library for manipulator motion planning

Using Catalyst.RL to train a robot to perform peg-in-hole insertion in simulation.