Posts

I recently started grad school and one of the classes I am taking is Natural Language Processing (NLP). Before the class I decided to watch a few videos on NLP and came across N-Grams. I have not made it known in any of my past posts but I love N-Grams. One of my projects is around reinforcing N-Grams which I hope to post about sometime later this year. Digression aside, I decided it would be a fun project to write an n-gram that uses the text of Harry Potter as input and see what we get; I know it isn’t the most original idea but it was fun. ...

A few months ago I completed the annual ProcJam jam. I wish I had considered doing a postmortem beforehand when everything was fresh, but now I am preparing for 7DRL. I figure a retrospective on how I did in the last jam will be useful for the upcoming one. Before beginning, I would like to preface this with the fact that I was sick for the entire jam. It’s not an excuse but it is one of the reasons why I did not complete as much as I would have liked to in the game. My original design was a weapon based roguelike, minus turn-based, where the player is trying to get through as many levels as possible. The weapons would be dropped by enemies and they would be adversarially generated. Meaning, a player that spams weapon shots would receive guns that shoot slower. A player that was extremely accurate would receive guns that would spray, such as a shotgun. In addition, all levels would be procedurally generated. I hoped to get in a few enemies and had a stretch goal of creating a boss. Lastly, I hoped to make the game a platformer. In short, I had an ambitious scope for a ten-day jam even if I wasn’t sick. ...

I want to go over Q-learning (a form of reinforcement learning) in this post. To start, we could go in two directions. We could explore at the bottom and look at the math behind neural networks and Q-learning. Or we could start at the top and see the end result. We are going to go with the latter. Figure 1: The mountain car environment. To do this we are going to need a few libraries and a testbed. To test, we are going to use OpenAI’s Gym and use MountainCar-V0. In this environment, proposed by Andrew Moore in his Ph.D. thesis, the car must reach the flag seen in figure 1. The car, though, does not have enough acceleration to achieve this by just going forward. Instead, it must go back and forward, steadily gaining enough speed to reach the goal. This is a problem that can be solved simply with a rule-based agent, however, reinforcement approaches can struggle with this. You’ll soon see that the amount of episodes it takes for q-learning to solve this is more than expected. ...

One day at work, I walked by someone who was going through a large set of PDFs and for everyone he put a block box over the name field. He mentioned it would take him several hours to accomplish this extremely menial task. Naturally, I found myself attracted to the problem due to my love of automation. I decided then and there I would write a small script that he could use to redact large set of similarly formatted PDFs. ...

I came across a youtube video which showed a way to visualize fractal trees. I watched it while eating dinner and didn’t think much of it at the time. A week or two later, though, I had decided to a do a few more challenges for my challenges repository and this was at the top of the list. It is a fairly simple program that has a cool end result seen in figures one and four. ...

A Quick Note I ended up getting pretty sick and I was out of commission for about two months. The good news is that I’m now in perfectly good health. The bad news is that it kind of destroyed my hopes of building a decent submission for GDMC. The competition ends in about thirteen days which is not enough time to come up with a submission I would be proud of. In addition, my 40+ hours at the Brain Game Center, where I work, every week is the very large nail in the coffin. Regardless, I plan on continuing to work on this problem until I have something cool I can show off. ...

If you’ve read my previous posts, then you know I love python. Regardless, it has been a goal of mine to be proficient in c++. I’m not exactly sure why I’m fascinated with this language that I have no uses cases for, but I think it stems from my love of video games. C++ is used extensively by my favorite company, Blizzard Entertainment, and sees a wide range of use across the industry. In addition, it also is apart of a field that is of particular interest for me, AI. For example, tensorflow is implemented in c++. ...

Source Control and GitHub GitHub is an awesome website that allows you to have unlimited repositories, for free, that are backed up with git on a remote server. In addition, it provides you with helpful tools like issues that allow you to keep track of bugs, features, and anything else you want. It is not the end all be all of source control and has pros and cons that should be considered before being used. ...

This is the first in a series of posts where I discuss implementing a version of Unblock Me and Rush Hour; sample screen shots can be seen in figure one. For the implementation, I’ve decided to use Python 2.7, however, you should be able to follow along with any language. My hope is that each of these posts will be more than just a copy and paste tutorial. To facilitate this, I will be taking deep dives into design decisions, test-driven design, common game AI architecture, general software structure, requirements gathering, servers, and more. ...

Generative Design in Minecraft (GDMC) GDMC is a competition to generate settlements within a selection of a minecraft map. The project’s website provides details on how the competition works and what is expected. However, the main point to get across right now is that they are judging based on adaptability, functionality, narrative, and aesthetics. Adaptability is about the generation technique working with the map rather than ignoring it. An example of ignoring the environment would be generating a wooden village where there are no trees. The functionality component is based on real world criteria such as access to food, defenses, etc. The narrative component is about how every area has a story to tell. An example is a castle with part of the tower knocked down. Lastly, aesthetics is about how it looks both in terms of believability and general appeal. ...