Skip to main content

Rei - Blog Post 7

Since the beginning of the semester, Matthew and I have been woking hard on the Replay Parser and Frame Collector. Both of these parts are crucial to the success of our project. With the first Demo of our project done also comes the completion of this first milestone.



Parsing the replay exposed some interesting information to us about how inputs are recorded, and therefore how the game sees them. Our original understanding of inputs was that multiple inputs would actually be spread out across multiple frames, however this was not true. It turns out that a frame is followed by a list of events which take place on that frame. We also learned that some human actions translate into multiple inputs. For example:

If you are using the control stick to move your character and you hold right on the control stick, your character moves right. One may think that this means the action RIGHT_PRESS is input, in actuality a list of actions is generated.

The list may look something like : {ANGLE___0, RIGHT_TAP, RIGHT_PRESS}.
Where: 
    ANGLE___0 means that a control stick is being held right.
    RIGHT_TAP means that the right action has been tapped. (Starts the Run Action)
    RIGHT_PRESS means that the right action has been pressed. (Continues the Run Action)

This is important to note the angles as using it means that Actions that take place in different directions can happen simultaneously. (Moving Right while Attacking Up).

The source code for the parser can be found here. I plan to add in-depth documentation for this python code in the GitHub, I also hope to upload the code onto PiPy as a module so it can be added to a python environment directly with pip.

Because this is the first replay tool for Rivals of Aether that I have seen, I would like to release it back to the community that helped make this project viable.


Finally, the last thing that I did during this break was create the Demo for out project. This involved packaging together frames and action sets. This was actually quite an easy task, because of all the preemptive work Matthew and I put in. The frames were already synced pretty well with the replay file, after some minor adjustments it was pretty much perfect.

As stated earlier, the code for the demo is quite simple. It follows a very simple set of actions:

  1. Create a list.
  2. Grab all the frame .npy files.
  3. For each .npy, create a tuple (frame_num, frame) and add it to the list.
  4. Grab all actions from a replay file.
  5. For each action, create a tuple (frame_num, action) and add it to the list.
  6. Sort the list by the first element in the tuple.
  7. Pair actions with the nearest frame following them.
Then, in order to present the pairing. We just output the frame to a png, and the action_list to a .txt, both of which can be read by other programs. When we want to move on to the next frame, we overwrite the temp png and txt.

The source code for the demo can be found here.

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 …