Reinforcement Learning on a rust simulation that only gives delayed rewards.
-
Updated
Apr 29, 2026 - Python
#
skrl
Here are 7 public repositories matching this topic...
Staged, reproducible RL hyperparameter search for Isaac Lab + skrl: declare a task in one YAML, run screen → refine → verify with fair canonical evals, live early-stop of dead runs, shared-GPU guards and termination-cause reports. A winner only counts after it reproduces.
machine-learning reinforcement-learning robotics amp hyperparameter-optimization hyperparameter-tuning hpo automl ppo isaac-sim skrl isaac-lab
-
Updated
Aug 4, 2026 - Python
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.
reinforcement-learning amp locomotion humanoid-robot motion-tracking ppo waypoint-navigation isaac-sim skrl isaac-lab unitree-g1 rsl-rl
-
Updated
Aug 16, 2026 - Python
NVIDIA Isaac Lab / Isaac Sim task: train Unitree G1 humanoid to run and jump obstacle-course hurdles. Hierarchical RL with AMP locomotion, frozen BeyondMimic motion tracker (nepher-ai/humanoid-g1-tracking), and PPO high-level run/jump switcher. Clips from Hugging Face bones-studio/seed. skrl. Gym: Nepher-G1-Run, Jump, RunJumpHL.
reinforcement-learning amp humanoid motion-tracking ppo obstacle-course isaac-sim skrl isaac-lab unitree-g1 beyondmimic
-
Updated
Aug 16, 2026 - Python
A robot-arm reinforcement learning project built with NVIDIA Isaac Lab, following the "Train Your Second Robot in Isaac Lab!" module. Trains a robotic arm to reach target positions and orientations using RL policies in Isaac Sim, with configurable environments for training and evaluation.
reinforcement-learning robotics simulation pytorch universal-robots ur10 gymnasium robotic-manipulation pose-tracking isaac-sim nvidia-omniverse skrl isaac-lab
-
Updated
Sep 2, 2026 - Python
Gridworld problem with dynamic obstacles implemented in PyGame GUI and solved using traditional RL agent (Q-learning) and deep RL agent (PPO algorithm).
pygame rl-agents reinforcement-learning-algorithms gridworld reinforcement-learning-agent gridworld-environment pygame-gui q-learning-algorithm ppo-agent ppo-pytorch skrl ppo-algorithm
-
Updated
Apr 15, 2026 - Python
Add this topic to your repo
To associate your repository with the skrl topic, visit your repo's landing page and select "manage topics."