Active Learning for Classifying 2D Grid-Based Level Completability

TL;DR

This paper explores using active learning to efficiently classify the completability of 2D grid-based game levels, improving classifier performance with fewer labeled examples.

Contribution

It introduces an active learning approach for level completability classification and demonstrates its effectiveness over random querying in multiple games.

Findings

Active learning improves classifier accuracy with fewer labeled levels.

Active learning outperforms random sampling in level classification tasks.

The approach is validated on levels from Super Mario Bros., Kid Icarus, and a Zelda-like game.

Abstract

Determining the completability of levels generated by procedural generators such as machine learning models can be challenging, as it can involve the use of solver agents that often require a significant amount of time to analyze and solve levels. Active learning is not yet widely adopted in game evaluations, although it has been used successfully in natural language processing, image and speech recognition, and computer vision, where the availability of labeled data is limited or expensive. In this paper, we propose the use of active learning for learning level completability classification. Through an active learning approach, we train deep-learning models to classify the completability of generated levels for Super Mario Bros., Kid Icarus, and a Zelda-like game. We compare active learning for querying levels to label with completability against random queries. Our results show using an active learning approach to label levels results in better classifier performance with the same amount of labeled data.