Playing the System: Can Puzzle Players Teach us How to Solve Hard Problems?

要旨

With nearly three billion players, video games are more popu- lar than ever. Casual puzzle games are among the most played categories. These games capitalize on the players’ analytical and problem-solving skills. Can we leverage these abilities to teach our- selves how to solve complex combinatorial problems? In this study, we harness the collective wisdom of millions of players to tackle the classical NP-hard problem of multiple sequence alignment, relevant to many areas of biology and medicine. We show that Borderlands Science players propose solutions to multiple sequence alignment tasks that perform as well or better than standard approaches, while exploring a much larger area of the Pareto-optimal solution space. We also show the strategies of the players, although highly het- erogeneous, follow a collective logic that can be mimicked with Behavioral Cloning with minimal performance loss, allowing the players’ collective wisdom to be leveraged for alignment of any sequences.

著者
Renata Mutalova
McGill University, Montréal, Quebec, Canada
Roman Sarrazin-Gendron
McGill University, Montréal, Quebec, Canada
Eddie Cai
McGill University, Montreal, Quebec, Canada
Gabriel Richard
Gearbox Studio Québec, Quebec, Quebec, Canada
Parham Ghasemloo Gheidari
McGill, Montreal, Quebec, Canada
Sébastien Caisse
Gearbox Studio Québec, Québec, Quebec, Canada
Rob Knight
UC San Diego, La Jolla, California, United States
Mathieu Blanchette
McGill University, Montreal, Quebec, Canada
Attila Szantner
Massively Multiplayer Online Science, Monthey, Switzerland
Jérôme Waldispühl
McGill University, Montreal, Quebec, Canada
論文URL

https://doi.org/10.1145/3544548.3581375

動画

会議: CHI 2023

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2023.acm.org/)

セッション: Social and Eduation in Games

Hall G2
6 件の発表
2023-04-25 18:00:00
2023-04-25 19:30:00