.png){kind=icon}
.png){kind=icon}
Return
Semi-Supervised Tile Embeddings: A General, Multigame Level Representation
.png){kind=icon}
PRE
AI
DOI：10.1109/TG.2025.3617866.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Representing video game levels for level generation and analysis tasks remains an open problem. Existing approaches generally rely on hand-authoring or are game-specific. Tile embeddings are a general machine learned-representation for tile-based game levels, however they have thus far relied solely upon hand-authored representations of levels for training data. In this article, we introduce semi-supervised tile embeddings (SSTE), which make use of semi-supervised learning to allow for training on levels lacking human authored representations. We evaluate SSTE over many experiments, finding that it performs equivalently or better than existing tile embeddings. Thus, SSTE stands as the first general machine-learned level representation that can scale without requiring additional human labor.
Keywords:
Games
Training
Affordances
Vectors
Autoencoders
Image edge detection
Tiles
Visualization
Video games
Solids
Machine learning
procedural content generation
representation learning