Skip to content

Latest commit

 

History

History
53 lines (42 loc) · 3.08 KB

Training-on-Amazon-Web-Service.md

File metadata and controls

53 lines (42 loc) · 3.08 KB
Raw

Training on Amazon Web Service

This page contains instructions for setting up an EC2 instance on Amazon Web Service for use in training ML-Agents environments. Current limitations of the Unity Engine require that a screen be available to render to. In order to make this possible when training on a remote server, a virtual screen is required. We can do this by installing Xorg and creating a virtual screen. Once installed and created, we can display the Unity environment in the virtual environment, and train as we would on a local machine.

Pre-Configured AMI

A public pre-configured AMI is available with the ID: ami-30ec184a in the us-east-1 region. It was created as a modification of the Amazon Deep Learning AMI.

Configuring your own Instance

Instructions here are adapted from this Medium post on running general Unity applications in the cloud.

  1. To begin with, you will need an EC2 instance which contains the latest Nvidia drivers, CUDA8, and cuDNN. There are a number of external tutorials which describe this, such as:
  2. Move python to remote instance.
  3. Install the required packages with pip install ..
  4. Run the following commands to install Xorg: 
    sudo apt-get update
sudo apt-get install -y xserver-xorg mesa-utils
sudo nvidia-xconfig -a --use-display-device=None --virtual=1280x1024
  5. Restart the EC2 instance.

Launching your instance

  1. Make sure there are no Xorg processes running. To kill the Xorg processes, run sudo killall Xorg.
    Note that you might have to run this command multiple times depending on how Xorg is configured.
    If you run nvidia-smi, you will have a list of processes running on the GPU, Xorg should not be in the list.

  2. Run:

    sudo /usr/bin/X :0 &
export DISPLAY=:0

  3. To ensure the installation was succesful, run glxgears. If there are no errors, then Xorg is correctly configured.

  4. There is a bug in Unity 2017.1 which requires the uninstallation of libxrandr2, which can be removed with :

sudo apt-get remove --purge libwxgtk3.0-0v5
sudo apt-get remove --purge libxrandr2

This is scheduled to be fixed in 2017.3.

Testing

If all steps worked correctly, upload an example binary built for Linux to the instance, and test it from python with:

from unityagents import UnityEnvironment

env = UnityEnvironment(your_env)

You should receive a message confirming that the environment was loaded succesfully.