An investigation into 2048 AI strategies

Philip Rodgers; John Levine

doi:10.1109/CIG.2014.6932920

An investigation into 2048 AI strategies

Philip Rodgers, John Levine

Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

2048 is a recent stochastic single player game, originally written in JavaScript for playing in a web browser but now largely played on mobile devices [1]. This paper discusses the applicability of Monte-Carlo Tree-Search (MCTS) to the problem, and also Averaged Depth Limited Search (ADLS). While MCTS plays reasonably well for a player with no domain knowledge, the ADLS player fares much better given an evaluation function that rewards board properties. Attempts to guide the roll-outs of MCTS using an evaluation function proved fruitless.

Original language	English
Title of host publication	2014 IEEE Conference on Computational Intelligence and Games
Publisher	IEEE
Number of pages	2
ISBN (Electronic)	9781479935475
DOIs	https://doi.org/10.1109/CIG.2014.6932920
Publication status	Published - 23 Oct 2014

Publication series

Name
ISSN (Print)	2325-4270
ISSN (Electronic)	2325-4289

Keywords

artificial intelligence
Monte Carlo methods
tree searching
computer games

Documents and Links

10.1109/CIG.2014.6932920

Fingerprint Dive into the research topics of 'An investigation into 2048 AI strategies'. Together they form a unique fingerprint.

Cite this

Rodgers, P., & Levine, J. (2014). An investigation into 2048 AI strategies. In 2014 IEEE Conference on Computational Intelligence and Games IEEE. https://doi.org/10.1109/CIG.2014.6932920

@inproceedings{8a86531222b34aceb56dd1a655b26887,

title = "An investigation into 2048 AI strategies",

abstract = "2048 is a recent stochastic single player game, originally written in JavaScript for playing in a web browser but now largely played on mobile devices [1]. This paper discusses the applicability of Monte-Carlo Tree-Search (MCTS) to the problem, and also Averaged Depth Limited Search (ADLS). While MCTS plays reasonably well for a player with no domain knowledge, the ADLS player fares much better given an evaluation function that rewards board properties. Attempts to guide the roll-outs of MCTS using an evaluation function proved fruitless.",

keywords = "artificial intelligence, Monte Carlo methods, tree searching, computer games",

author = "Philip Rodgers and John Levine",

note = "Changed template from conference paper 6/02/2020 ",

year = "2014",

month = oct,

day = "23",

doi = "10.1109/CIG.2014.6932920",

language = "English",

publisher = "IEEE",

booktitle = "2014 IEEE Conference on Computational Intelligence and Games",

}

TY - GEN

T1 - An investigation into 2048 AI strategies

AU - Rodgers, Philip

AU - Levine, John

N1 - Changed template from conference paper 6/02/2020

PY - 2014/10/23

Y1 - 2014/10/23

N2 - 2048 is a recent stochastic single player game, originally written in JavaScript for playing in a web browser but now largely played on mobile devices [1]. This paper discusses the applicability of Monte-Carlo Tree-Search (MCTS) to the problem, and also Averaged Depth Limited Search (ADLS). While MCTS plays reasonably well for a player with no domain knowledge, the ADLS player fares much better given an evaluation function that rewards board properties. Attempts to guide the roll-outs of MCTS using an evaluation function proved fruitless.

AB - 2048 is a recent stochastic single player game, originally written in JavaScript for playing in a web browser but now largely played on mobile devices [1]. This paper discusses the applicability of Monte-Carlo Tree-Search (MCTS) to the problem, and also Averaged Depth Limited Search (ADLS). While MCTS plays reasonably well for a player with no domain knowledge, the ADLS player fares much better given an evaluation function that rewards board properties. Attempts to guide the roll-outs of MCTS using an evaluation function proved fruitless.

KW - artificial intelligence

KW - Monte Carlo methods

KW - tree searching

KW - computer games

U2 - 10.1109/CIG.2014.6932920

DO - 10.1109/CIG.2014.6932920

M3 - Conference contribution

BT - 2014 IEEE Conference on Computational Intelligence and Games

PB - IEEE

ER -