Extension of RSL-RL for using Morphological Symmetries in IsaacLab
-
Updated
Sep 2, 2026 - Python
Extension of RSL-RL for using Morphological Symmetries in IsaacLab
RL training pipeline for LimX TRON2A humanoid — Isaac Lab + PPO (rsl_rl), Sole-Foot & Wheel-Foot variants.
Isaac Lab RL project for a two-wheel balancing robot with equivalent leg mapping and wheel-ground contact debugging
Extension of RSL-RL for using Mixture-of-Experts in IsaacLab
A full-stack Embodied AI simulation suite powered by Genesis World: featuring OpenVLA closed-loop evaluation, procedural scene generation, massively parallel GPU RL (Unitree Go2), and multi-physics coupling (PBD/SPH).
Official OneRobotics A1 integration for mjlab — MJCF model, reach task, RSL-RL training, and validation.
The collection of rsl_rl compatible envs for the Aegis station.
COM-guided Dropbear humanoid locomotion in NVIDIA Isaac Lab with RSL-RL PPO, live viewer, robot USD, and validated checkpoints
GPU-parallel RL training workspace for NVIDIA Isaac Lab: ANYmal locomotion + Franka reach with RSL-RL PPO, scripts, and 8GB-VRAM defaults.
NVIDIA Isaac Lab / Isaac Sim task for Unitree G1 humanoid RL: whole-body motion tracking, hierarchical AMP locomotion (skrl), and waypoint racing. Race PPO (10 Hz) commands a frozen AMP actor over a frozen tracker (50 Hz). Train with RSL-RL; EnvHub-reproducible race eval. Nepher Robotics.
Reproducible Isaac Lab quadruped locomotion project with robustness evaluation, policy export contracts, and ROS 2 hardware-interface.
Deep Reinforcement Learning (PPO) for 31-DoF Humanoid Bipedal Locomotion and In-Place Jumping using NVIDIA Isaac Sim 4.0, IsaacLab, and RSL-RL.
Lite3 四足机器人强化学习训练与 MuJoCo Sim-to-Sim 部署
NavRL Bench trains reinforcement learning policies from scratch using IsaacLab / Isaac Sim and compares the trained RL local controller against classical Nav2 controllers such as DWB, MPPI, and RPP.
Deep Reinforcement Learning (PPO) framework for training Unitree Go2 quadruped robots to dynamic ball-kicking tasks in NVIDIA Isaac Lab using RSL-RL.
Research fork of NVIDIA Isaac Lab that trains a 23-DoF Unitree G1 to reproduce a reference jump with RSL-RL: a six-phase jump task, CSV reference-motion loader, phase-weighted tracking rewards, and a sim-to-real deployment toolchain. main tracks upstream; check out integration/all.
Modular reinforcement learning pipeline for legged robot locomotion in Genesis, inspired by Unitree pipelines and designed for scalable sim-to-real transfer.
已合并至 money12532/Lite3_RL_Project(强化学习训练部分)
To associate your repository with the rsl-rl topic, visit your repo's landing page and select "manage topics."