Isaac Orbit environments

Isaac Orbit environments

Environments

The repository https://github.com/NVIDIA-Omniverse/Orbit provides the example reinforcement learning environments for Isaac orbit

These environments can be easily loaded and configured by calling a single function provided with this library. This function also makes it possible to configure the environment from the command line arguments (see Running an RL environment) or from its parameters as a python dictionary

Note

The command line arguments has priority over the function parameters

Note

Isaac Orbit environments implement a functionality to get their configuration from the command line. Setting the headless option from the trainer configuration will not work. In this case, it is necessary to invoke the scripts as follows: python script.py --headless

Basic usage

1# import the environment loader
2from skrl.envs.torch import load_isaac_orbit_env
3
4# load environment
5env = load_isaac_orbit_env(task_name="Isaac-Cartpole-v0")

API

skrl.envs.torch.loaders.load_isaac_orbit_env(task_name: str = '', show_cfg: bool = True)

Load an Isaac Orbit environment

Isaac Orbit: https://isaac-orbit.github.io/orbit/index.html

This function includes the definition and parsing of command line arguments used by Isaac Orbit:

  • --headless: Force display off at all times

  • --cpu: Use CPU pipeline

  • --num_envs: Number of environments to simulate

  • --task: Name of the task

  • --num_envs: Seed used for the environment

Parameters

  • task_name (str, optional) – The name of the task (default: “”). If not specified, the task name is taken from the command line argument (--task TASK_NAME). Command line argument has priority over function parameter if both are specified

  • show_cfg (bool, optional) – Whether to print the configuration (default: True)

Raises

ValueError – The task name has not been defined, neither by the function parameter nor by the command line arguments

Returns

Isaac Orbit environment

Return type

gym.Env