paper-with-me

홈 › Papers

Open-World Skill Discovery from Unsegmented Demonstrations

2025-03-11 · Jingwen Deng, ZiHao Wang, Shaofei Cai, Anji Liu, Yitao Liang

Learning skills in open-world environments is essential for developing agents capable of handling a variety of tasks by combining basic skills. Online demonstration videos are typically long but unsegmented, making them difficult to segment and label with skill identifiers. Unlike existing methods that rely on sequence sampling or human labeling, we have developed a self-supervised learning-based approach to segment these long videos into a series of semantic-aware and skill-consistent segments. Drawing inspiration from human cognitive event segmentation theory, we introduce Skill Boundary Detection (SBD), an annotation-free temporal video segmentation algorithm. SBD detects skill boundaries in a video by leveraging prediction errors from a pretrained unconditional action-prediction model. This approach is based on the assumption that a significant increase in prediction error indicates a shift in the skill being executed. We evaluated our method in Minecraft, a rich open-world simulator with extensive gameplay videos available online. Our SBD-generated segments improved the average performance of conditioned policies by 63.7% and 52.1% on short-term atomic skill tasks, and their corresponding hierarchical agents by 11.3% and 20.8% on long-horizon tasks. Our method can leverage the diverse YouTube videos to train instruction-following agents. The project page can be found in https://craftjarvis.github.io/SkillDiscovery.

📄 PDF Abstract BibTeX arXiv:2503.10684

Code (0)

등록된 구현이 없습니다.

Tasks

Boundary DetectionEvent SegmentationInstruction FollowingMinecraftSelf-Supervised LearningVideo SegmentationVideo Semantic Segmentation

Similar Papers 제목 키워드 기반

Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation

2021-09-28 · Yifeng Zhu, Peter Stone, Yuke Zhu

We tackle real-world long-horizon robot manipulation tasks through skill discovery. We present a bottom-up approach to learning a library of reusable skills from unsegmented demonstrations and use these skills to synthes…

Imitation LearningRobot Manipulation

LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery

2023-11-03 · Weikang Wan, Yifeng Zhu, Rutav Shah, Yuke Zhu

We introduce LOTUS, a continual imitation learning algorithm that empowers a physical robot to continuously and efficiently learn to solve new manipulation tasks throughout its lifespan. The core idea behind LOTUS is con…

Imitation LearningLifelong learningRobot ManipulationTransfer Learning

Transfering Hierarchical Structure with Dual Meta Imitation Learning

2022-01-28 · Chongkai Gao, Yizhou Jiang, Feng Chen

Hierarchical Imitation Learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations. However, the learned hierarchical structure lacks the mechanism to transfer across mu…

Few-Shot Imitation LearningImitation LearningMeta-Learning

Transferring Hierarchical Structure with Dual Meta Imitation Learning

2021-09-29 · Chongkai Gao, Yizhou Jiang, Feng Chen

Hierarchical Imitation learning (HIL) is an effective way for robots to learn sub-skills from long-horizon unsegmented demonstrations. However, the learned hierarchical structure lacks the mechanism to transfer across mu…

Few-Shot Imitation LearningImitation LearningMeta-Learning

Symskill: Symbol and Skill Co-Invention for Data-Efficient and Reactive Long-Horizon Manipulation

2025-10-02 · Yifei Simon Shao, Yuchen Zheng, Sunan Sun, Pratik Chaudhari 외 arxiv

Multi-step manipulation in dynamic environments remains challenging. Imitation learning (IL) is reactive but lacks compositional generalization, since monolithic policies do not decide which skill to reuse when scenes ch…

Motion Planning