Reinforcement Learning

Using Reinforcement Learning to Play 2048 Apr 9, 2026 | 14 min read

And dominating my friend's "Weddy-48" leaderboard

I explored some reinforcement learning methodologies for 2048—yes, the 12-year-old tile sliding game. Mostly as a learning exercise, but also to crush the top scores on my friend’s custom, “uncommonly smooth” beer-themed 2048 implementation.