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.


Popular posts from this blog

Matthew - Capstone Blog Post 1

First I would like to discuss our goals and long-term plans. We want to create an artificial intelligence that learns how to play first-person shooters without access to any game state data other than what can be gained through the audio and visual buffers. In other words, the AI will only have access to the information that a human player would. If we are successful with these constraints, then I could see our work leading to AI that can play any game, or even AI-driven robots that can play games using mechanical hands and eyes to operate normal peripherals and interfaces.

We are currently in the research and planning phase of the project. This means that our job right now is to decide exactly what tools and technologies we will use and how they will interact with one another. By the end of the semester, which will arrive sometime this December, we will need to be ready for phase two, which is the development, training, and testing phase. Yes, that is all three at once. However, if …

Rei - Capstone Blog Post 1

Over the past couple of weeks, Matthew and I have been trying to narrow down our idea for capstone. We have settled on a "Modular" AI that can play First Person Shooters or other similar video games. However, we decided to put a slight twist on the idea of an AI playing games. Most of the AIs that are currently out have more information than they should possibly have at that time, like the location of players. We decided that our AI would only have information that would be accessible to a human player. We also noticed that many of the "PlayerAIs" out there are reactionary, not planning. While reacting is a key part to many of these games, so is strategy. We want to create an AI that thinks, at least a little bit, about that actions it is making or should make.

Since narrowing down our topic we have split off and started looking at different existing technologies and research that could help us understand and create this project. I decided to look at some computer…

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 …