# Isaac Lab Basics[#](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-lab/latest/isaac-lab-basics/index.html.md#isaac-lab-basics 'Link to this heading')

This module puts the concepts from [Robot Learning Fundamentals](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-lab/latest/robot-learning-fundamentals/index.html.md) into practice. You’ll explore Isaac Lab and its related frameworks, physics engines, and libraries, generate a new project, and train and inspect a cartpole policy. The generated example gives you a small task to follow from configuration through manager execution and policy playback before you build the SO-101 task in [Train a Robot Arm](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-lab/latest/train-a-robot-arm/index.html.md).

If you’re ready for a more complex task, you can skip ahead to [Train a Robot Arm](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-lab/latest/train-a-robot-arm/index.html.md) and return to this module later.

[An env_cfg.py map pairs the generated cartpole configuration classes with their runtime task managers. BalanceSceneCfg creates InteractiveScene, BalancePhysicsCfg selects PhysicsManager, and a lower strip traces env.step through cart effort, two physics steps, task evaluation, and the next observation.](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-lab/latest/_images/isaac-lab-manager-system.svg)

Isaac Lab connects scene and physics configuration with managers that handle actions, observations, events, rewards, and episode endings. Together, these components turn a task description into a running simulation.[#](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-lab/latest/isaac-lab-basics/index.html.md#id1 'Link to this image')

By the end of this module, you’ll understand the concepts shown in the figure.

Learning Objectives

- Explain how Isaac Lab connects robot learning tasks, physics backends, and learning libraries.

- Generate a cartpole project and find its task registration, environment configuration, and Proximal Policy Optimization (PPO) configuration.

- Set up a local or remote development workflow and keep a record of experiment settings and outputs.

- Describe how managers handle actions, observations, resets, rewards, and episode endings.

- Use the Isaac Lab CLI to run zero-action and random-action baselines, train a PPO policy, and play saved checkpoints.

- Compare training metrics and policy playback with baselines to assess learning progress and identify further reliability checks.

Code blocks with a **thicker green border** contain commands to run or code to copy into your project as part of the lesson. Follow the instructions above each block to choose the terminal or file. Blocks without this border show reference examples, expected output, or optional activities.

[A thicker green border marks commands to run or code to copy into the named file. A standard border marks reference examples, expected output, or optional activities.](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-lab/latest/_images/code-block-border-guide.svg)

Use the border and the surrounding instructions to identify what to do with each code block.[#](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-lab/latest/isaac-lab-basics/index.html.md#id2 'Link to this image')

Use the _activities_ to check your understanding as you go. Here are some tips for completing them:

- Make a prediction about the outcome of a command before running it.

- After running a command, change one thing and describe what you observe.

- Answer the understanding question before opening its answer or hint.

- Use an agent to quiz yourself on the learning objectives.