CS 467 Learning About Unity and Machine Learning

After the previous weeks of working on various tutorials and learning different facets of Unity, this week we are focusing on finishing the basic version of Breakout with no machine learning. This has required a lot of linking different game objects to each other in order to share information between the different objects. Since we are working in teams this has also required closer coordination with my teammates than on previous objects since things can break due to unforeseen consequences of changing something in either Unity or in scripting.

The bright side is seeing everything coming together. This week I have primarily been focused on menus and the game over condition is handled correctly. It was nice being able to play through a full game and see the life tracker tick down when I failed and have a game over condition trigger. This made it feel like a more complete project. There is still definitely work to be done still, such as adding additional difficulty due to levels or decreasing the paddle size in subsequent panels. However, its always nice to see progress on a project.

I started doing Unity tutorials and setting up my environment this week. I’m doing this so I can learn about how to make a version of Breakout that uses machine learning with my teammates.

So far I’ve made a clone of Flappy bird according to one tutorial. The funniest thing I learned while doing this is to remember to change tags after creating them. While I was making a tag I thought it would autoassign it, since I created the tag in the field for a specific object, but I was wrong. This led to a fair amount of troubleshooting until I continued the tutorial and found out what mistake I had made.

One of the things I like about Unity so far is how much coding is involved while using it. It has made learning it feel more familiar than just learning a new tool, as I get too build on my previous experience.

Hello, I am John Hamrang. I used to work as a structural analysis engineer in the aerospace industry before realizing I didn’t want to do that anymore, so I chose to pursue a career in computer science. This post is going to be light, as I’ve just been assigned to the machine learning breakout project!

I have not worked with machine learning before beyond some structural optimization methods that use similar equations, so I am excited to learn more about that with this project. In addition to this I haven’t worked with Unity in the past. I have worked with Unreal engine a bit, so its not the first game engine I am working with, but I am looking forward to learning more about it.

I am happy with this project as I used to play some of the breakout clones that existed, and it involves learning a lot of things that I don’t have much experience with. I think this is going to be a fun class.