Weakly-Supervised Trajectory Segmentation for Learning Reusable Skills

2019-09-25 · Parsa Mahmoudieh, Trevor Darrell, Deepak Pathak

Learning useful and reusable skill, or sub-task primitives, is a long-standing problem in sensorimotor control. This is challenging because it's hard to define what constitutes a useful skill. Instead of direct manual supervision which is tedious and prone to bias, in this work, our goal is to extract reusable skills from a collection of human demonstrations collected directly for several end-tasks. We propose a weakly-supervised approach for trajectory segmentation following the classic work on multiple instance learning. Our approach is end-to-end trainable, works directly from high-dimensional input (e.g., images) and only requires the knowledge of what skill primitives are present at training, without any need of segmentation or ordering of primitives. We evaluate our approach via rigorous experimentation across four environments ranging from simulation to real world robots, procedurally generated to human collected demonstrations and discrete to continuous action space. Finally, we leverage the generated skill segmentation to demonstrate preliminary evidence of zero-shot transfer to new combinations of skills. Result videos at https://sites.google.com/view/trajectory-segmentation/

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple Instance Learning Segmentation

Weakly-Supervised Learning of Disentangled and Interpretable Skills for Hierarchical Reinforcement Learning

2021-09-29 · Wonil Song, Sangryul Jeon, Hyesong Choi, Kwanghoon Sohn 외

Hierarchical reinforcement learning (RL) usually requires task-agnostic and interpretable skills that can be applicable to various downstream tasks. While many recent works have been proposed to learn such skills for a p…

Decoder Hierarchical Reinforcement Learning Inductive Bias reinforcement-learning+2

Offline Discovery of Interpretable Skills from Multi-Task Trajectories

2026-02-01 · Chongyu Zhu, Mithun Vanniasinghe, Jiayu Chen, Chi-Guhn Lee arxiv

Hierarchical Imitation Learning is a powerful paradigm for acquiring complex robot behaviors from demonstrations. A central challenge, however, lies in discovering reusable skills from long-horizon, multi-task offline da…

Language-guided Skill Learning with Temporal Variational Inference

2024-02-26 · Haotian Fu, Pratyusha Sharma, Elias Stengel-Eskin, George Konidaris 외

We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical var…

Segmentation Variational Inference

VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience

2026-08-17 · Jianming Chen, Xuanbin Ye, Yawen Wang, Junjie Wang 외 arxiv

Agents increasingly rely on reusable skills to encode task knowledge, tool-use procedures, and validation rules. Existing skill self-evolution methods primarily revise skills using execution trajectories collected from c…

Unsupervised Hierarchical Skill Discovery

2026-01-30 · Damion Harvey, Geraud Nangue Tasse, Benjamin Rosman, Branden Ingram 외 arxiv

We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent approaches have sought to segment trajectories into reusable skills or options, most…

Reinforcement Learning