This project explores building a Reinforcement Learning (RL) Neural Network that can learn to play the classic game Snake autonomously. Unlike rule-based AI, this network learns through trial and error, gradually discovering optimal strategies for survival and score maximization.
Inspiration
I’ve always been fascinated by AI that learns on its own, without explicit instructions. Watching reinforcement learning applications like AlphaGo and OpenAI Gym examples inspired me to apply these concepts to a simpler, approachable game: Snake. I wanted to see if a neural network could develop human-like intuition for navigating and growing in a dynamic environment.

Log in or sign up for Devpost to join the conversation.