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

This is an official GitHub Repository for paper "Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach".

Official Code for "Relative Entropy Pathwise Policy Optimization"

official implementation of CVPR 2026 paper: Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation (Null-TTA)

Coursework 1 for Robot and Reinforcement Learning (INFR11285) at University of Edinburgh

RCareWorld simulation environment for caregiving robots

This is a official code for the benchmark of the paper "VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement Learning" (ICLR 2025)

[ICLR25 Oral] RL framework for manipulation of diverse shapes and deformable objects

Awesome Manipulation

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research

An RL library for training multimodal robotic agents in Isaac Lab.

RoTO is an open-source Reinforcement Learning benchmark environment designed to standardise and promote future research in tactile-based manipulation.

This repo contains the training logs, checkpoints, and plots for "Enhancing Tactile-based RL for Robotic Control", with instructions for how to playback the agents

Official implementation of COT Policy

PyTorch implementation of the InfoNCE loss for self-supervised learning.

Tactile Sensing • IL/RL/VLA/WM • Manipulation • Representation • Simulation • Open Source

Implementation of Zorro, Masked Multimodal Transformer, in Pytorch

SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learning

Unified framework for robot learning built on NVIDIA Isaac Sim

External extenstion template based on Isaac Lab

Code for the 2024 RLC Paper "Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL"

A curated list of awesome NVIDIA Issac Gym frameworks, papers, software, and resources

RL implementations

Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras

DMControl Generalization Benchmark

Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning

For Visuo-Tactile Transformers for Manipulation