Snake AI

In another somewhat machine learning related project, I decided to create a Snake Game AI. My main objective was to create an AI that could not only collect the apples (which is a common goal in Snake games), but also complete the game by filling out the board. To do this, I explored a variety of different models and algorithms, trying out different approaches and tweaking my parameters to see what worked best.

One of the challenges I faced in this project was finding a way to balance the trade-off between exploration and exploitation. On the one hand, the Snake AI needed to explore the game board and try out different strategies in order to find the most efficient path to completion. On the other hand, it also needed to be able to exploit its knowledge of the game and make smart, calculated moves in order to maximize its chances of success.

In the end, I was able to create a Snake Game AI that was able to complete the game with a high degree of efficiency, but interestingly enough not better than I could do manually step by step. Overall snake game requires a significant amount of foresight. It was a challenging and rewarding project that allowed me to explore the latest advances in machine learning and apply my skills to a fun and engaging problem.