O'Reilly logo

Learn Unity ML-Agents - Fundamentals of Unity Machine Learning by Micheal Lanham

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

The Bouncing Banana

If you want to be more accurate in a simulation or game, you may want to set different reaction times for different input signals or events. For instance, you may only want an agent to react after it hits an object or trigger, thus not requiring the agent brain to react to a null input. Unity implemented a feature in ML-Agents called On-Demand Decision Making, which allows an agent to wait before making a decision. Unity, of course, has a sample for this, so let's open up the editor and follow this exercise:

  1. Locate and open the Bouncer scene in the Assets/ML-Agents/Examples/Bouncer folder.
  2. Find and select the BouncerBrain in the Hierarchy window. Set the Brain Type to Internal and make sure the Graph Model is set to a ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required