Search Results for author:
Found 6 papers, 3 papers with code
Simulator-Free Visual Domain Randomization via Video Games
In a more challenging setting, BehAVE manages to improve the zero-shot transferability of foundation models to unseen FPS games (up to 22%) even when trained on a game of a different genre (Minecraft).
Towards General Game Representations: Decomposing Games Pixels into Content and Style
On-screen game footage contains rich contextual information that players process when playing and experiencing a game.
Game State Learning via Game Scene Augmentation
Having access to accurate game state information is of utmost importance for any artificial intelligence task including game-playing, testing, player modeling, and procedural content generation.
Revisiting lp-constrained Softmax Loss: A Comprehensive Study
Normalization is a vital process for any machine learning task as it controls the properties of data and affects model performance at large.
Learning Task-Independent Game State Representations from Unlabeled Images
We train an image encoder with three widely used SSL algorithms using solely the raw frames, and then attempt to recover the internal state variables from the learned representations.
Contrastive Learning of Generalized Game Representations
In this paper we build on recent advances in contrastive learning and showcase its benefits for representation learning in games.
Ranked #1 on
Image Classification
on Sports10
