The Unity Machine Learning Agents Toolkit (ML-Agents Toolkit for short) is a collection of software and plugins that help writing autonomous game agents powered by machine learning algorithms. You can explore and download the source code at the GitHub repository at https://github.com/Unity-Technologies/ml-agents.
The ML-Agents Toolkit is based on the reinforcement learning algorithm. In a very simplistic way, reinforcement learning is the algorithmic equivalent of training a dog. If you want to teach a dog some trick, you give him a command and then, when the dog does what you expect, you give him a reward. The reward tells your dog that it is responding correctly to a command and, therefore, the next time it hears the same command, it will do the same thing to get a new reward:
