Autor: Martin Haring

In the previous two weeks I covered an introduction to the ML-Agents Toolkit and explained examples that make use of it. Using that information, I applied the toolkit to a final project – a modified version of the Bouncer example, which I named Climber.

In this final blog, I report on my final project.

Last week I discovered and introduced the ML-Agents toolkit, which is a Unity utility that applies Machine Learning to Unity applications. A first look on the kart racing example project provided insights into this specific field. In summary, an RL agent receives some form of input and improves its behavior based on that input over time until its performance reaches a desired degree of quality. On the one hand, this utility fulfills my initial goal to test applications using AI while on the other hand, it even surpasses my intentions by providing extra features, like training NPCs.

In this blog, example projects of the ML-Agents toolkit are briefly shown and summarized.

When I covered libraries, frameworks and toolkits, I missed out on a potentially game-chaning toolkit, which I will dive into today.

In this blog, I take a first-hand look on the Unity Machine Learning-Agents Toolkit.

When I originally analyzed MarI/O and did my research for Metroid Learning, I skipped over the very basics of this field that is Goal Driven Systems. Thus, it is time to catch up on a bit of theory.

In this blog, I introduce goal-driven systems, reverse engineering and emulators.

Researching on the topic lead to the conclusion that I skipped one of the most important steps – assigning Reinforcement Learning (RL) bots their place in the field of Artificial Intelligence (AI). There is a lot of ground to cover, so it is now time to catch up on it.

In this blog, I properly introduce RL’s place in the field AI.

In this blog, I take the first steps in the practical development process, which include choosing the working environment, naming the project and setting up the GitHub repository.

New blog series starting today; the final arc of my work: tool development.

In this diary-formatted blog, I summarize the progress made so far and try to create a small to do list for myself.

This blog is about hyperparamaters and some tuning methods for them.

This blog is about the policy-iteration method Proximal Policy Optimization (PPO).

This blog serves as an introduction to policy gradient methods.