728x90
반응형
VALAN: Vision and Language Agent Navigation
VALAN is a lightweight and scalable software framework for deep reinforcement learning based on the SEED RL architecture. The framework facilitates the development and evaluation of embodied agents for solving grounded language understanding tasks, such as
arxiv.org
[37]VALAN Vision and Language Agent Navigation-arXiv1912.pptx
0.39MB
논문을 깊게 읽고 만든 자료가 아니므로, 참고만 해주세요. 얕은 지식으로 모델의 핵심 위주로만 파악한 자료이다 보니 없는 내용도 많습니다. 혹시 사용하실 경우 댓글 부탁드립니다.
728x90
반응형
'Paper Reading > Vision and Language Navigation(VLN)' 카테고리의 다른 글
| BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby steps (0) | 2020.08.18 |
|---|---|
| Vision-Dialog Navigation by Exploring Cross-modal Memory (0) | 2020.08.18 |
| Cross-Lingual Vision-Language Navigation (0) | 2020.08.18 |
| Environment-agnostic Multitask Learning for Natural Language Grounded Navigation (0) | 2020.08.18 |
| Multi-View Learning for Vision-and-Language Navigation (0) | 2020.08.18 |
