Your custom trainers are responsible for collecting experiences and training the models. We use code snippets and patterns to demonstrate the control and data flow. The purpose of the tutorial is to introduce you to the core components and interfaces of our plugin framework. We will not provide a workable code in the document. Please refer to the internal PPO implementation for a complete code example. You can either extend OnPolicyTrainer or OffPolicyTrainer classes depending on the training strategies you choose. Let us follow an example by implementing a custom trainer named "YourCustomTrainer". Users of the plug-in system are responsible for implementing the trainer class subject to the API standard. The following command uses conda, but other tools work similarly: conda create -n trainer-env python=3.8.13 venv or conda) to create and activate a Python virtual environment. Custom Trainer Plugin Step 1: Write your custom trainer classīefore you start writing your code, make sure to use your favorite environment management tool(e.g.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |