I have finally finished my literary review, and it has been super cool finding more examples of games that use PCG. I think It would be really neat if I could figure out a way to implement an algorithm in a way to make my game infinite! Its also amazing how far PCG has come from Rouge which was basically the first to now, were some games are much more complex and intricate.

This past week, I spent countless hours working on my Final Paper.  I also spent a considerable amount of time working to correct errors and bugs in my code inside of MaxMSP.

This week I continued debugging my code. I now have everything I need working working. It’s not as good as I think it can be, but it is fully operational. Spent a little time starting paper revisions and that’s next up.

Still polishing the paper. Been revising section by section and created a new diagram for the paper.

Need to fix an issue with the citations.

Will make time to try and tweak the experiment for the paper to see if I can get different result.

1. The spring break week dealt with mapping MIDI control into the acoustics of the three-dimensional space, which I have successfully done.
2. I have also successfully added an FIR based buffer into the program as well to track analytics. You use buffir~ object when you need a finite impulse response (FIR) filter that convolves an input signal with samples from an input buffer. With that, you can look at an FIR filter response graph in MaxMSP which calculates the filter response of the FIR in the main sound patch for a given number of samples (coefficients)

Created and ran experiment. Noted the results down.

Finished the first draft of the Capstone paper. Currently revising and polishing it.

This week I turned in a new draft of my paper and fixed a few bugs. I am now ready to collect most of the data I’ll need.

This week I have dealt with working on improving my final paper and working on the MIDI mapping and audio of my project inside MaxMSP. I primarily worked on getting the audio format correctly to be able to loop and connect each file with the object associated in the three-dimensional space within MaxMSP.  I secondly worked on the formatting of my paper; it needed to flow from topic to topic more also recognizing why it was relevant to the project as a whole.

This week I

-implemented feedback from the first draft

-started writing the rest of the paper

-did some minor debugging and commenting

Built a functioning, testable (not yet accurate) Neural Network that takes in my input of heuristic data and output a direction.

Since the puzzle states were strings, I wanted the output to be the value added to the index of the “_” to move to a new position but negative values cannot be used as targets or labels in neural network so instead I coded them using values 0-3 to represent each move.

I created a function that takes in the output of the neural network and converts it to a move for the puzzle.

Also know which specific layers I need to experiment with make my neural network be accurate.