paper-with-me

홈 › Papers

Skill Induction and Planning with Latent Language

2021-10-04 · ACL 2022 5 · Pratyusha Sharma, Antonio Torralba, Jacob Andreas

We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative model of action sequences in which goals generate sequences of high-level subtask descriptions, and these descriptions generate sequences of low-level actions. We describe how to train this model using primarily unannotated demonstrations by parsing demonstrations into sequences of named high-level subtasks, using only a small number of seed annotations to ground language in action. In trained models, natural language commands index a combinatorial library of skills; agents can use these skills to plan by generating high-level instruction sequences tailored to novel goals. We evaluate this approach in the ALFRED household simulation environment, providing natural language annotations for only 10% of demonstrations. It achieves task completion rates comparable to state-of-the-art models (outperforming several recent methods with access to ground-truth plans during training and evaluation) while providing structured and human-readable high-level plans.

📄 PDF Abstract BibTeX arXiv:2110.01517

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Skill Induction and Planning with Latent Language

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative…

Decision MakingInstruction Following

Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks

2026-05-02 · Jie-Jing Shao, Haiyan Yin, Yueming Lyu, Xingrui Yu 외 arxiv

Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into…

Inducing Programmatic Skills for Agentic Tasks

2025-04-09 · Zora Zhiruo Wang, Apurva Gandhi, Graham Neubig, Daniel Fried

To succeed in common digital tasks such as web navigation, agents must carry out a variety of specialized tasks such as searching for products or planning a travel route. To tackle these tasks, agents can bootstrap thems…

SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution

2023-12-18 · CVPR 2024 1 · Zhixuan Liang, Yao Mu, Hengbo Ma, Masayoshi Tomizuka 외

Diffusion models have demonstrated strong potential for robotic trajectory planning. However, generating coherent trajectories from high-level instructions remains challenging, especially for long-range composition tasks…

Trajectory Planning

Learning Skills from Action-Free Videos

2025-12-23 · Hung-Chieh Fang, Kuo-Han Hung, Chu-Rong Chen, Po-Jung Chou 외 arxiv

Learning from videos offers a promising path toward generalist robots by providing rich visual and temporal priors beyond what real robot datasets contain. While existing video generative models produce impressive visual…