ML-Agents Video Streamer

Now you can Live Stream the Agent's learning behavior to Twitch/YouTube from Google Colab while training these Agents.

What’s In This Document

• Installation
• Imports and Usage
• License

Installation

!pip install mlagents-video-streamer

And if you already have mlagents-video-streamer then upgrade it by this command.

!pip install --upgrade mlagents-video-streamer

Imports and Usage

from mlagents_video_streamer import SetupVirtualDisplay
from mlagents_video_streamer import VideoStreamer

• Now Setup the Virtual Display:

  SetupVirtualDisplay()
  

• Define your live stream information:

  # stream_info dictionary should be in this format only
  stream_info = {
      "URL": "rtmp://live.twitch.tv/app/", # example of Twitch URL
      "secret": "--- secret here ---"
  }
  

• Initialize the VideoStreamer class with stream_info:

  videoStreamer = VideoStreamer(stream_info)
  

  *If you don't pass stream_info then it will simply store the video locally in the videos directory.

• Start the video streamer before starting with the training process:

  videoStreamer.start()
  

• Now capture the training process, using subprocess library:

  import subprocess
  from random import randrange
  
  try:
      train = subprocess.run([
          "mlagents-learn", 
          "config.yaml",
          "--run-id=train-1",
          "--env=3DBall_example/3DBall.x86_64",
          "--base-port=" + str(randrange(9000, 9999))
      ],
          cwd="/content/", stdout=subprocess.PIPE)
      print("Training process has been successfully ended.")
  except Exception as e:
      print("You killed the training process in between.")
  finally:
      videoStreamer.close()
  

  *At the end don't forget to close the video streamer by using close() method on videoStreamer object as shown in the above example.

License

Licensed under the MIT License.