GridWorld – v1.0

-
My second assignment was to create a pathfinding program called GridWorld, not unlike an old AP Case Study.

User Interface

Again my first priority was the interface. Using the trusty library StdDraw, I used the same sort of grid pattern that I used in my Game of Life program. This time, by using images to form the grid instead of individual rectangles, I didn't have to worry about borders between the cells or any other extra buffer. The final UI can be seen in the picture. 


However, this time, instead of creating buttons on the canvas itself, I opted to use Swing, the GUI toolkit included in Java. This helped me create buttons and a "Control Panel" (right), which was much easier than using StdDraw's graphics and listening for a mouse click.
The Game

As we are learning about Agents in my Artifical Intelligence class, this project contains an Agent, which is the player. The Agent loops through three phases: sense, decide, and act. In Gridworld, the Player agent senses which paths are open and which are blocked, decides which way it should go based on that information, and finally acts by moving to the appropriate cell. 

GridWorld's rules are simple. First, the player builds a maze made of bricks and roads. Keep in mind that when building, the road pathways must be at least two blocks wide. After building a maze, the player can add/remove players (a green circle) and exits (a blue square), and can also reset cells to their default states (roads for most, walls for the outer border). See the picture below for an example maze.


After that, the player clicks go and then the program runs. The game finishes when a player (the green circle) finds an exit. 

Future Improvements

Although I am proud of this project, I believe there is definitely room for improvement. Updating the graphics for the players and exits could be a great benefit. Also, giving the user more preferences for the game would be great. For example, the user could choose which way the player moves through the maze (left or right); the textures (sprites) for the players; and whether all players, or just one of them, needs to exit to finish the game.

Additionally, I think it would be neat to add a "battle mode", where players fight each other if they are in close proximity to each other in the maze. 

Download

(coming soon, still trying to figure out where to host these files)

Comments

Post a Comment

Popular updates

Half Moon Project Part 2 - More Accuracy

-
Image
This time around, we used the Neuroph library to create a neural network  that can divide the double half-moons more accurately. Neural Networks A Neural Network is a combination of Neurons that feed into each other. Using some really complex math, they can weight each input (from a previous Neuron) differently. Then, after training, they can use backpropagation to calculate which weights should be edited. What this looks like can be seen below. More Accuracy for Half-Moons Since, previously, we were only using one neuron to calculate the line to separate the two moons, we could only draw a linear line. This time, with a more complex neural network, it can separate the two with a function that's super complicated. Theoretically, a human could also derive the equation, but it's so complex that at this point, it's easier to get the Neural Network to do it for us.
Read more

NumberVision – Machine Learning Application

-
Image
The next way we used our Neuron class was to classify digits. Using a UI, our program was assigned to take an input digit (a 5x7 grid, each box has a shade of grey between black and white) and classify the digit as a number between 0 and 9. A Smarter Neuron Graphical depiction of a Neuron receiving more than 2 inputs. Previously, I had only been using a Neuron with two inputs: an X and Y coordinate. Previously, this allowed me to plot my points on a plane like I did with the Half Moon project. However, due to the 5x7 grid of inputs I was getting, I had to alter my Neuron class to be able to take in 35 inputs. Mostly, this involved changing a few numbers.  Applying the Neuron to NumberVision The digit '1', with progressively more noise added from left to right. Good algorithms should be able to generate a result even if the input is a little distorted. I applied the same goal to NumberVision. The flow chart above shows various levels of added distortio
Read more

Machine Learning & Half Moon Project

-
Image
This was our first Machine Learning assignment. Machine Learning is something that I was (and still am) super excited about. Basically, the algorithm 'learns' something, and can then apply it in other situations. Learning & Neurons This was the toughest concept to learn (ha). We started with a Neuron, similar to the neurons in our brains. The neuron can trigger (yes/no) based on a series of inputs, in our case two inputs. The equation for whether or not the neuron triggers is SUMMATION(Weight(n) * Input(n)) > threshold . Each input is weighted differently, and the weights are what we can change to 'train' the neuron. We use this equation:  ΔWeight = learningSpeed * (target - output) * input . For example, if we start with a speed of 0.2, an input of 1, a weight of 0.5, and a target of 0, the weight would change by -0.2 (0.2 * (1 - 0) * 1). Now, with a weight of 0.3, repeat the process. Once each input returns the desired output, the best weights have been fo
Read more