/drlnd-soccer

Deep Reinforcement Learning Nanodegree, Optional Challenge: Play Soccer.

Primary LanguageASP.NET

Deep Reinforcement Learning Nanodegree Challenge: Play Soccer

Introduction

For this project, you will work with the Tennis environment.

Soccer In this environment, the goal is to train a team of agents to play soccer.

You can read more about this environment in the ML-Agents GitHub here. To solve this harder task, we'll need to download a new Unity environment.

Project Setup

  1. You need only select the environment that matches your operating system:

  1. Place the file in the environments/ folder, and unzip (or decompress) the file.

  2. [Optional] Create a Conda environment and activate it

(base) ➜  drlnd-soccer git:(master) ✗ conda create --name drlnd-soccer python=3.6
(base) ➜  drlnd-soccer git:(master) ✗ conda activate drlnd-soccer

  1. Change into the python folder and execute pip install . to install the required dependencies.

  2. Create a custom IPython kernel by executing $ python -m ipykernel install --user --name drlnd --display-name "drlnd"

Getting Started

Start a jupyter notebook from within the project folder and follow the instructions in notebooks/Soccer.ipynb to either

  • train your own agent or
  • load the model weights and watch the pre-trained agent

HINT: make sure to switch from the default Python 3 kernel to "drlnd" (see section Project Setup).

Tested on macOS Big Sur (Version 11.0.1) and Ubuntu 20.04.2 LTS.