Papers › Contrastive Learning of Generalized Game Representations

Contrastive Learning of Generalized Game Representations

18 Jun 2021arXiv:2106.10060archive 2025-07-28

Chintan Trivedi, Antonios Liapis, Georgios N. Yannakakis

Representing games through their pixels offers a promising approach for building general-purpose and versatile game models. While games are not merely images, neural network models trained on game pixels often capture differences of the visual style of the image rather than the content of the game. As a result, such models cannot generalize well even within similar games of the same genre. In this paper we build on recent advances in contrastive learning and showcase its benefits for representation learning in games. Learning to contrast images of games not only classifies games in a more efficient manner; it also yields models that separate games in a more meaningful fashion by ignoring the visual style and focusing, instead, on their content. Our results in a large dataset of sports video games containing 100k images across 175 games and 10 game genres suggest that contrastive learning is better suited for learning generalized game representations compared to conventional supervised learning. The findings of this study bring us closer to universal visual encoders for games that can be reused across previously unseen games without requiring retraining or fine-tuning.

PaperPDFCode

Code

ChintanTrivedi/contrastive-game-representations officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningImage ClassificationRepresentation Learning

Datasets

Introduced by this paper, per the archive.

Sports10

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification Sports10 Max Margin Contrastive Validation Accuracy 93.42 #1 of 1 Archive leaderboard report
Representation Learning Sports10 Max Margin Contrastive Silhouette Score 0.56 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive LearningSupervised Contrastive Loss

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections