The AI of the computer player is an RNN, which is a type of neural network. The objective of the game, what the controls do, and strategies were never hard coded into the AI, it learned them through trial and error, the way a human would. It's a lightweight implementation too, done in JS. One neat feature is that you can see the real-time activations of the neurons which are connected to the control nodes in the background.
Is the "learned" behavior stored in the javascript somewhere, or is it coming from a socket in real time? Is it just a giant data array for handling possible decisions?
Yeah, there are a total of 140 weights/biases in the neural network. This stuff is not bleeding edge - just taking techniques popular in academia and industry many years ago to make a fun game mainly for my own educational purpose. Basically recently I saw a lot of work on AI's playing ATARI games and wanted to learn reinforcement learning techniques, and the best way to learn is to build a game!
Basically, the agent's brain consists of 7 neurons (compared to 250k for an ant), which are connected to all the inputs. The inputs are the game states, like locations of agents and ball, and velocities. Each neuron is also connected to each other.
The first 3 neurons control the neuron's output (it's motor function), like whether it hits the up, forward, or back button - the same function that a human game player can do.
The other 4 neurons are hidden neurons responsible for any deeper computation or thought, and are fed back into the input with a time lag.
I also graphed a slice of the neural network in real time on the screen just for effect. More for design effect if anything.
Do you mind helping me truncate the length of the message above with the number array? It's causing issues on browser sessions not word wrapping messages
