| CARVIEW |
Select Language
HTTP/2 200
content-type: text/html; charset=utf-8
x-cloud-trace-context: ae0cac9969b85404f66da1999c773316
cache-control: max-age=3600
server: Google Frontend
last-modified: Thu, 15 Dec 2022 01:15:33 GMT
x-frame-options: SAMEORIGIN
content-security-policy: frame-ancestors 'none'
via: 1.1 google, 1.1 varnish, 1.1 varnish, 1.1 varnish
accept-ranges: bytes
age: 697747
date: Thu, 01 Jan 2026 00:11:04 GMT
x-served-by: cache-lga21942-LGA, cache-lga21973-LGA, cache-bom-vanm7210043-BOM
x-cache: MISS, HIT, MISS
x-timer: S1767226264.312708,VS0,VE211
content-length: 46664
[2212.07407] Cross-Domain Transfer via Semantic Skill Imitation
Skip to main content
We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors.
Donate
Computer Science > Machine Learning
arXiv:2212.07407 (cs)
[Submitted on 14 Dec 2022]
Title:Cross-Domain Transfer via Semantic Skill Imitation
Authors:Karl Pertsch, Ruta Desai, Vikash Kumar, Franziska Meier, Joseph J. Lim, Dhruv Batra, Akshara Rai
View a PDF of the paper titled Cross-Domain Transfer via Semantic Skill Imitation, by Karl Pertsch and 6 other authors
View PDF
Abstract:We propose an approach for semantic imitation, which uses demonstrations from a source domain, e.g. human videos, to accelerate reinforcement learning (RL) in a different target domain, e.g. a robotic manipulator in a simulated kitchen. Instead of imitating low-level actions like joint velocities, our approach imitates the sequence of demonstrated semantic skills like "opening the microwave" or "turning on the stove". This allows us to transfer demonstrations across environments (e.g. real-world to simulated kitchen) and agent embodiments (e.g. bimanual human demonstration to robotic arm). We evaluate on three challenging cross-domain learning problems and match the performance of demonstration-accelerated RL approaches that require in-domain demonstrations. In a simulated kitchen environment, our approach learns long-horizon robot manipulation tasks, using less than 3 minutes of human video demonstrations from a real-world kitchen. This enables scaling robot learning via the reuse of demonstrations, e.g. collected as human videos, for learning in any number of target domains.
| Comments: | Project website: this https URL |
| Subjects: | Machine Learning (cs.LG); Robotics (cs.RO) |
| Cite as: | arXiv:2212.07407 [cs.LG] |
| (or arXiv:2212.07407v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2212.07407
arXiv-issued DOI via DataCite
|
|
| Journal reference: | CoRL 2022 |
Full-text links:
Access Paper:
- View PDF
- TeX Source
View a PDF of the paper titled Cross-Domain Transfer via Semantic Skill Imitation, by Karl Pertsch and 6 other authors
References & Citations
export BibTeX citation
Loading...
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
IArxiv Recommender
(What is IArxiv?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.