Training a visual agent
Unity develops a 2D and 3D gaming engine/platform that has become the most popular platform for building games. Most of these games are the 3D variety, hence the specialized interest by Unity in mastering the task of agents that can tackle more 3D natural worlds. It naturally follows then that Unity has invested substantially into this problem and has/is working with DeepMind to develop this further. How this collaboration turns out remains to be seen, but one thing is for certain is that Unity will be our go-to platform for exploring 3D agent training.
In the next exercise, we are going to jump back into Unity and look at how we can train an agent in a visual 3D environment. Unity is arguably the best place to set ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access