Hunter

Image of game

Inspiration

We were inspired by how neural networks grow and improve over time, learning from feedback and adapting their behavior. This reminded us of personal growth—how people learn from their mistakes and get better through practice. We wanted to create a project that reflects this growth through gameplay.

What it Does

Our game is a grid-based chase game where you, the player, try to escape from an AI-controlled enemy. But the twist is that the enemy gets smarter as it learns from its mistakes. Using a neural network, the enemy improves over time, growing its skills to catch you.

How We Built It

We used: Python and Pygame: To build the game world and handle player movement. PyTorch: To train the enemy AI with reinforcement learning so it could adapt and grow its strategies over time.

Challenges We Ran Into

Training the AI to actually learn and improve without making random moves. Helping the AI figure out the best way to chase the player while keeping the gameplay fun.

Accomplishments That We're Proud Of

We successfully trained an AI that improves as it plays, showing real growth over time. We worked well as a team and built more than we expected within the limited time.

What We Learned

How neural networks grow through learning from rewards and mistakes. The basics of Pygame and game development. The importance of teamwork and communication in achieving big goals.

What’s Next for Hunters

We’d love to: Make the AI even smarter by using more advanced training methods. Add new game features like obstacles or power-ups to make it more exciting. Let players train their own AI enemies and watch them grow in skill.