AIOct 20, 2021
Playing 2048 With Reinforcement Learning
arXiv:2110.10374v1
Originality Synthesis-oriented
AI Analysis
This is an incremental improvement for game AI enthusiasts, as it applies existing methods to a challenging puzzle game.
The paper tackled the problem of winning the game 2048 using reinforcement learning, with beam search achieving a 2048 tile 28.5% of the time.
The game of 2048 is a highly addictive game. It is easy to learn the game, but hard to master as the created game revealed that only about 1% games out of hundreds million ever played have been won. In this paper, we would like to explore reinforcement learning techniques to win 2048. The approaches we have took include deep Q-learning and beam search, with beam search reaching 2048 28.5 of time.