Sun Sep 11 2022
Thu Sep 01 2022

Transformers are Sample Efficient World Models

Sequence modeling
Artificial Intelligence
Machine Learning
Reinforcement learning
Game AI
Transformers

IRIS, a data-efficient agent that learns in a world model composed of a discrete autoencoder and an autoregressive Transformer, achieves a mean human normalized score of 1.046, and outperforms humans on 10 out of 26 games in the Atari 100k benchmark.

IRIS shows promise in improving sample efficiency in reinforcement learning and sets a new state-of-the-art for methods without lookahead search.

Visual Prompting via Image Inpainting

Image inpainting
Artificial Intelligence
Machine Learning
Computer vision
Image processing
Visual AI

Visual prompting, posed as simple image inpainting, is effective when the inpainting algorithm is trained on the right data. This approach was demonstrated on various image-to-image tasks, including foreground segmentation, single object detection, colorization, edge detection, etc.

Visual prompting offers a promising way to adapt pre-trained visual models to novel downstream tasks without task-specific finetuning or model modification.

Tue Aug 30 2022
Sun Aug 28 2022
Thu Aug 25 2022
Wed Aug 24 2022