Humanoidbench RL#

We provide a basic RL training example for Humanoidbench tasks.

RL framework: stable-baselines3

RL algorithm: PPO

Simulator: MuJoCo and IsaacGym and IsaacLab

Installation#

pip install stable-baselines3
pip install wandb
pip install tensorboard

Wandb login, enter your wandb account token.

wandb login

Training#

NOTE:

  1. Modify task: humanoidbench:Stand in the config files to the task you want to train.

  2. Modify use_wandb: true and wandb_entity: <your_wandb_entity_name> in the config files to use wandb to log the training process.

  • MuJoCo:

    python roboverse_learn/humanoidbench_rl/train_sb3.py mujoco

  • IsaacGym:

    python roboverse_learn/humanoidbench_rl/train_sb3.py isaacgym

  • IsaacLab:

    python roboverse_learn/humanoidbench_rl/train_sb3.py isaaclab

Task list#

  • Balance

    • Not Implemented because of collision detection issues.

  • Crawl

  • Cube

  • Door

  • Highbar

    • Not implemented due to the need to connect H1 and Highbar.

  • Hurdle

    • Not Implemented because of collision detection issues.

  • Maze

    • Not Implemented because of collision detection issues.

  • Package

  • Pole

    • Not Implemented because of collision detection issues.

  • Powerlift

  • Push

  • Run

  • Sit

  • Slide

  • Spoon

    • Not Implemented because of sensor detection issues.

  • Stair

  • Stand