Tue Jun 14 2022
Mon Jun 13 2022

Large-Scale Retrieval for Reinforcement Learning

Machine Learning
Reinforcement Learning
Improving game-play performance in RL

The use of large-scale retrieval significantly improves prediction accuracy and game-play performance in RL.

This approach allows agents to directly learn in an end-to-end manner to utilize relevant information to inform their outputs, without retraining, by simply augmenting the retrieval dataset. This provides a significant boost to prediction accuracy and game-play performance over simply using these demonstrations as training trajectories.

ARF: Artistic Radiance Fields

Artificial Intelligence
Computer Vision
Creating high-quality artistic 3D content

Creates high-quality artistic 3D content by transferring the style of an exemplar image, such as a painting or sketch, to NeRF and its variants.

This method can transfer the artistic features of an arbitrary style image to a 3D scene, making it possible to create photorealistic and artistically stylized content. It outperforms baselines in generating artistic appearance that more closely resembles the style image.

Tue Jun 07 2022
Mon Jun 06 2022