Lune

ICLR2025Top-tier venue

SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks

Yijie Guo, Bingjie Tang, Iretiayo Akinola, Dieter Fox, Abhishek Gupta, Yashraj Narang

Abstract

Enabling robots to learn novel tasks in a data-efficient manner is a long-standing challenge. Common strategies involve carefully leveraging prior experiences, especially transition data collected on related tasks. Although much progress has been made for general pick-and-place manipulation, far fewer studies have investigated contact-rich assembly tasks, where precise control is essential. We introduce SRSA (Skill Retrieval and Skill Adaptation), a novel framework designed to address this problem by utilizing a pre-existing skill library containing policies for diverse assembly tasks. The challenge lies in identifying which skill from the library is most relevant for fine-tuning on a new task. Our key hypothesis is that skills showing higher zero-shot success rates on a new task are better suited for rapid and effective fine-tuning on that task. To this end, we propose to predict the transfer success for all skills in the skill library on a novel task, and then use this prediction to guide the skill retrieval process. We establish a framework that jointly captures features of object geometry, physical dynamics, and expert actions to represent the tasks, allowing us to efficiently learn the transfer success predictor. Extensive experiments demonstrate that SRSA significantly outperforms the leading baseline. When retrieving and fine-tuning skills on unseen tasks, SRSA achieves a 19% relative improvement in success rate, exhibits 2.6x lower standard deviation across random seeds, and requires 2.4x fewer transition samples to reach a satisfactory success rate, compared to the baseline. In a continual learning setup, SRSA efficiently learns policies for new tasks and incorporates them into the skill library, enhancing future policy learning. Furthermore, policies trained with SRSA in simulation achieve a 90% mean success rate when deployed in the real world. Please visit our project webpage https://srsa2024.github.io/.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Policy Compatible Skill Incremental Learning via Lazy Learning Interface cites Dynamics-Aware Unsupervised Discovery of Skills
  • Policy Compatible Skill Incremental Learning via Lazy Learning Interface cites A Definition of Continual Reinforcement Learning
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Policy Compatible Skill Incremental Learning via Lazy Learning InterfaceDaehee Lee, Dongsu Lee, TaeYoon Kwack, Wonje Choi et al.NeurIPS 2025 · 3 citations

Builds on11

  1. Dynamics-Aware Unsupervised Discovery of SkillsArchit Sharma, Shixiang Gu, Sergey Levine, Vikash Kumar et al.ICLR 2020 · 475 citations
  2. Multi-Task Reinforcement Learning with Context-based RepresentationsShagun Sodhani, Amy Zhang, Joelle PineauICML 2021 · 241 citations
  3. The Unsurprising Effectiveness of Pre-Trained Vision Models for ControlSimone Parisi, Aravind Rajeswaran, Senthil Purushwalkam, Abhinav GuptaICML 2022 · 233 citations
  4. A Definition of Continual Reinforcement LearningDavid Abel, André Barreto, Benjamin Van Roy, Doina Precup et al.NeurIPS 2023 · 167 citations
  5. UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist LearningWeikang Wan, Haoran Geng, Yun Liu, Zikang Shan et al.ICCV 2023 · 160 citations

Related papers

  1. Robust Fine-tuning of Vision-Language-Action Robot Policies via Parameter MergingYajat Yadav, Zhiyuan Zhou, Andrew Wagenmaker, Karl Pertsch et al.ICLR 2026 · 10 citations
  2. TDSS: Task Dynamic-Synergistic Skill Adaptation for Boosting Efficient and Scalable Multi-Task Learning in Dense Visual PredictionHaiming Yao, Qiyu Chen, Wei Luo, Zheng Zhang et al.AAAI 2026
  3. Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic ManipulationXitie Zhang, Aming WU, Yahong HanICML 2026
  4. GeCo-SRT: Geometry-aware Continual Adaptation for Cross-Task Sim-to-Real TransferWenbo Yu, Wenke Xia, Weitao Zhang, Di HuCVPR 2026
  5. STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy LearningMarius Memmel, Jacob Berg, Bingqing Chen, Abhishek Gupta et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines