Skip to main content

Rei - Captsone Blog Post 3

Over the past couple of weeks, progress on this project has been slow but meaningful. Matthew and I have decided to do a temporary re-scoping of the project. Instead of focusing on a 3-D game, we are going to move to a simpler 2-D game. The game is the only real change we have made though, as we still want it to infer a game state from the visual buffer.


The game we have chosen is the 2-D pixel fighter Rivals of Aether.


 We chose this game primarily because of how it outputs replay data. Rivals of Aether stores its replay data as plain-text. More specifically it stores input data as 'tuples' of (InputFrame, Input) for example '5134y' is saying press the 'Y' button on frame 5134. Using this we can gather more data for our RivalsAgent to learn from.


Currently, the plan Matthew and I have agreed upon is to work primarily with Rivals of Aether. If our implementation works well and we feel as if we can safely scope-up, we will move from Rivals to Quake.



As I promised in Post 2, I have also began looking into data flow in Neural Networks. From what research I have done and considering the scope of our project, I have found and begun research on two classes of neural networks. The neural networks are Feedforward Neural Networks and Recurrent Neural Networks.

Feedforward Neural Networks are the first and simplest type of neural network. Connections between units do not form a cycle. Information in A feed forward network moves in one direction. This leads to this type of network to be used for the "supervised learning of binary classifiers" meaning that an input either belongs to some class or does not. For example, a network that tries to find correlations between two related data sets could use feed-forward.

Recurrent Neural Networks on the other hand do have cycles. These cycles allow the network to use previously learned data to learn more about both the same data and similar data. Many recognition algorithims use these types of networks. For example, a Handwriting Recognition tool would need to learn about how the user writes letters, and then can use that data to learn how the user writes words and so on.

Combining feed forward and recurrent networks in modular systems has been done many times before, regardless our project will most likely combine these networks to reach our end goal.

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 …