Define Skills
Skills are the foundational building blocks for your intelligent agent. They take action to achieve goals in key scenarios where your agent needs to succeed. To build an agent with Machine Teaching, you will create multiple skills and then orchestrate them together.
You can use three different types of skill within Composabl.
Create a to implement a that uses DRL to make decisions. You can set up your teacher to train the skill using goals or to train with rewards. The skill will then train and practice in simulation until it can make decisions successfully.
Create a to implement a that makes decisions based on programming rather than learning. A controller can use math, rules, optimization, or any other technology that can be expressed in a Python program. Configure controllers with the SDK and publish them to the UI to use in agents.
Create a to orchestrate skills together. Selectors are specialized skills that direct the agent how to choose between different decision-making skills. Selectors can be either learned or programmed.
You can also create skills in two different ways, using the UI and using the SDK. If you use the SDK, you can then publish the skills to the UI to be included in agent designs.
For learned skills you can use either the UI or the SDK successfully to create teachers, but the SDK includes some fine-tuning options that are not available in the UI.
Controllers for programmed skills can be created only through the SDK. They can then be published to the UI for use in agents.
You can use either the UI or the SDK to create selectors.
Last updated