Demo Documentation
Documentation for Lab Rat Race, the demo project included with this plugin. This is directed at people who are reasonably comfortable with Unity, and new to working with neural networks and for people who just downloaded our plugin and want to know how to make use of our sample project.
DyNet Documentation
Dynet’s website includes thorough script documentation and tutorials for writing your own machine learning algorithms. This is a great resource for those who are familiar with machine learning, but new to DyNet’s library.
Dynamic Machine Learning
This overview on machine learning architecture should help you think about how you can utilize dynamic neural networks in your game or application, or help you get ideas of how to take your existing neural network and increase it’s visibility and usability.
F.A.Q.
DyNet is an open source neural network library for C++. It primarily spun out of Carnegie Mellon University, and has had many contributors over the years. It is a library built for efficient performance with dynamic structures that can adapt and change for different training instances. This makes the library particularly effective for natural language processing, and game AI that learns during runtime.
The power of AILIVE is in the flexibility of the library. You can learn more about writing and customizing your own neural network with DyNet in their documentation.
What is DyNet?
Do I need to know how to program machine learning?
You should have a solid grasp of the fundamental structures of machine learning systems. Understand what data you want to feed into the algorithm, what information you need to receive from the algorithm and at what frequency.
Included with the demos is a rudimentary AI controller, which should serve to get most projects off the ground, even if you have little to no experience with neural networks.
Where do I get the data from?
While you can use usual machine learning datasets (subject to their licencing) one of the key advantages to AILIVE is that you can generate data during gameplay and train your machine learning models with user actions, user generated content, environment states, or countless other sources from within your game’s scripts.
How is this different than state machine based AI?
Rather than AI only reacting to what the player does, DyNet could be used to actually change the way the AI thinks in response to the player. This unlocks a lot of new potential verbs for the player to take, such as “teach”, “praise”, “scold”, “reward”, and “punish” that have meaningful gameplay ramifications.
Additionally, beyond pre-tranined MLAs, DyNet integration allows you to include both the player and machine learning algorithms as a part of the game loop.
I downloaded AILIVE, but it will not compile!
The plugin does not work out of the box from Unity’s store because scripts need to be compiled in a certain order.
Make sure you move the Plugins folder from the AILIVE folder to the asset folder root
Make sure you set Scripting Runtime Version to .NET 4.x Equivalent (Edit > Project Settings > Player > Other Settings)
Restart Unity