Playing 2048 With Reinforcement Learning

2021-10-20Code Available0· sign in to hype

Shilun Li, Veronica Peng

Code Available — Be the first to reproduce this paper.

Code

github.com/Shilun-Allan-Li/2048-reinforcement_learning
Officialpytorch★ 7

Abstract

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.

Tasks

Playing the Game of 2048 Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Benchmark Results

Dataset	Model	Metric	Claimed	Verified	Status
The Game of 2048	Beam Search	Average Score	1,024	—	Unverified
The Game of 2048	DQN (1000 episodes)	Average Score	256	—	Unverified

Playing 2048 With Reinforcement Learning

Code

Abstract

Tasks

Benchmark Results

Reproductions