Skip to main content

Rei - Capstone Blog Post 2



This week, I wanted to look more deeply at current game AIs and try to get a deeper understanding of what Machine Learning AIs created for video games look like. I started by looking at one of the larger Computer Vision AIs, ViZDoom.




ViZDoom, according to the official website, is a "Doom-based AI research platform for reinforcement learning from raw visual information." ViZDoom sets out to accomplish a goal similar to ours, make an AI that can play Doom using only the screen buffer. The research group holds annual competitions, the competitions allows many developers to test their AI tweaks against others which results in some pretty competent AI players.


After looking into ViZDoom and learning about more Algorithms in AI, I decided to look at some of the really amazing Game AIs that are coming into public view. I found a video that explained AlphaGo. Which I found that I understood, at least understood better than I would have earlier. AlphaGo's math is pretty much a MiniMax algorithm and neural networks.


While I still don't completely understand everything explained in this video, I can tell that I am much closer than I was even last week. Now that I have at least implements some simple AIs(Basic Graph Searches), I understand how the data flow works a bit better.

My goals moving forward are to take a more in-depth look at simple neural networks. I would like to understand, at the very least, how data is stored and flows in a Neural Network problem. The other major goal I have for the upcoming weeks is to start listing the skills and resources that will be needed to complete this project.

Comments

Popular posts from this blog

Matthew - Capstone Blog Post 4

Finally, our CSI-480 (Advanced Topics: AI) course material is catching up to where we need to be. We are covering perceptrons and sigmoid neurons in the lectures, and we are also using TensorFlow to solve some very simple introductory problems (via tutorials). To supplement this I have been reading Neural Networks and Deep Learning by Michael Nielsen, a textbook available for free on the internet, which dives into neural networks right from the first chapter. Additionally, I have been finding 3Blue1Brown's multi-part video series about deep learning to be extremely helpful for visualizing some of the more advanced concepts. Even if I do not fully understand the calculus and linear algebra involved, at the very least I have a better idea of what goes on inside of neural networks. For example: I know what loss and gradient descentalgorithmsdo, essentially, and I also understand how the latter helps find a local minimum for the former, but I do not necessarily feel confident in my …

Matthew - Blog Post 9

After our last meeting, Professor Auerbach asked us to shift our focus towards building and training our model. So that's what we've been working on lately. The results so far have been interesting and problematic.

The first step was to define a minimal working model and a loading system to feed it our labelled data-set. I wrote a Sequence subclass, which is essentially a kind of generator designed for use with the fit_generator method. With fit_generator and a sequence, we're able to train and test the model with just a couple of one-liners:

model.fit_generator(sequence)
model.evaluate_generator(sequence)

The sequence subclass also has a few other tricks up its proverbial sleeve. For one, it reduces the dimensionality of the frame buffer data from 135×240×3 to 135×240×1 by converting it to gray-scale. This reduces the number of features from 97,200 to 32,400. For two, it does the same with the labels, combining and dropping 26 action types into just 9 atomic classes. This a…

Matthew - Blog Post 7

Since January, we've been working hard to not only finish writing the Replay Parser and Frame Collector but also totally synchronize them. I'm pleased to report our success. This is an amazing milestone for us because it means that we've surmounted one of our most troubling obstacles.


I have also made sure to keep our documentation up to date. So, if you like, you can follow along with this blog post by replicating its results.
The Frame Collector uses timed input sequences to start each replay associated with the currently running game version. Then, after waiting a set amount of time for playback to begin, it starts grabbing 1/4-scale frames at a rate of 10 frames per second. The Frame Collector takes these down-scaled frames, which are NumPy arrays, and rapidly pickles and dumps them into the file system. Here's a screenshot of the Frame Collector in action:

If you look at the image above, you'll see that each pickle (the .np files) is simply assigned …