Overview

2019.3

Anaconda Download & Install

Anaconda Environment Setup

Trainer Config YAML

Training Preparation

Training

Training Progress & Time Scale

Tensorboard

Importing .nn File & Inference

Re-training

Training Wrap-up & Challenge

Get an introductory overview of how training works when using ML-Agents in Unity.

Learn how to download and install Anaconda to prepare your development environment.

Learn to configure an Anaconda environment to install and manage ML-Agents.

Get an overview of the Trainer Config YAML file and how it defines training settings.

Set up a training scene and run the ML-Agents Python command from a virtual environment.

Discover how to run the training command to start a new training session.

Learn how to monitor and understand training progress directly within the scene.

Get an introduction to Tensorboard and how it supports visualizing training data and metrics.

Learn how to run inference in Unity using a fully trained agent.

Learn the core ideas behind continued training when working with ML-Agents in Unity.

Experiment with changing parameters and predict how those adjustments will affect the results in your scene.

In this project, we will set up Anaconda for Python management and train our agents. We'll talk about how to configure training, as well as how to monitor it. Once we have a successfully trained neural network, we'll import it to our project for inference.

78fd089b-6c0f-51a7-ae23-019069f0d8ca:6udFvAlfFjsjj7eis1j377

In this tutorial you will learn about Tensorboard.

Tensorboard

1. Tensorboard

Complete this Tutorial