Large-Scale Retrieval for Reinforcement Learning
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
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.