AI-Initiative-KAUST/VideoRLCS
Learning to Identify Critical States for Reinforcement Learning from Videos (Accepted to ICCV'23)
This tool helps machine learning researchers understand why their reinforcement learning (RL) agents behave the way they do, especially when learning from videos. It takes recorded videos of an agent's interactions or demonstrations and outputs an identification of the "critical states" – the moments in the video that significantly impact the outcome. This is ideal for RL practitioners who train agents and need to debug or improve their learning processes.
No commits in the last 6 months.
Use this if you need to pinpoint key decision points or influential moments in an agent's video-recorded behavior to understand or enhance its learning.
Not ideal if you are looking for a general-purpose video analysis tool or if your agents are not based on reinforcement learning.
Stars
29
Forks
3
Language
Python
License
—
Category
Last pushed
Aug 19, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/AI-Initiative-KAUST/VideoRLCS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yizt/cv-papers
计算机视觉相关论文整理、记录、分享; 包括图像分类、目标检测、视觉跟踪/目标跟踪、人脸识别/人脸验证、OCR/场景文本检测及识别等领域。欢迎加星,欢迎指正错误,同时也期待能够共同参与！！!...
DmitryRyumin/ICCV-2023-25-Papers
ICCV 2023-2025 Papers: Discover cutting-edge research from ICCV 2023-25, the leading computer...
extreme-assistant/CVPR2024-Paper-Code-Interpretation
cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理
gitzyong812/STIP
Code for CVPR22 paper: Exploring Structure-aware Transformer over Interaction Proposals for...
DmitryRyumin/WACV-2024-Papers
WACV 2024 Papers: Discover cutting-edge research from WACV 2024, the leading computer vision...