Lists (3)
Starred repositories
Official Pytorch Implementation of "Zero-Shot Off-Policy Learning" (ICML 2026)
Awesome Quadrupedal Robots
A C and Python library for physically accurate, real-time, sensor simulation and visualization using NVIDIA Omniverse RTX
A framework for training, evaluating, and comparing state-of-the-art zero-shot reinforcement learning methods. It allows reproducing the experiments of the paper "TD-JEPA Latent-predictive Represen…
Actuators Co-design and Task-aware Optimization for Robots
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
The official implementation of flow Q-learning (FQL)
cvoelcker / rsl_rl
Forked from leggedrobotics/rsl_rlA fast and simple implementation of learning algorithms for robotics.
Benchmarking GR00T N1 policy in Isaac Lab
AI agents running research on single-GPU nanochat training automatically
RL Extension Library for Robots, Based on IsaacLab.
Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"
TensorDict is a pytorch dedicated tensor container.
A curated list of mathematical optimization courses, lectures, books, notes, libraries, frameworks and software.
RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code
Curated repository of papers on integrating reinforcement learning with generative AI models in robotics, featuring categorized Excel summaries of key analysis metrics like frameworks, applications…
80
Updated Apr 23, 2026
two wheel legged robot for IsaacLab - reinforcement learning
Provides a ROS 2 control hardware interface for the MuJoCo physics simulator, including plugins for various sensors, RGB-D cameras, and lidar.
Cartpole minimal example using mjlab as external dependency
Differentiable Model Predictive Control on the GPU
Train a Unitree G1 humanoid to perform a double spin kick using mjlab
EO: Open-source Unified Embodied Foundation Model Series
Deep RL for MPC control of Quadruped Robot Locomotion
An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.