Internship : Robotic Skill Transfer Learning
at
NAVER LABS Europe
Description
Reinforcement learning (RL) offers significant potential for developing diverse and robust skills autonomously, without requiring expert demonstrations. However, learning a new complex skill model from scratch demands a large amount of robot experience and relies heavily on the robot's own exploration strategies. A promising approach to optimize this learning process is to leverage previously acquired skill models to accelerate the learning of new skills in different contexts (1).
Internship Overview:
In this internship, we will explore two different methods for skill transfer in reinforcement learning:
- Leveraging existing policies across different spaces: Reusing policies that accomplish the target skill but operate with different input (observation) and output (action) spaces, or that use alternative data and knowledge sources. Examples include policies trained on human demonstrations, hand-crafted motion controllers, and pre-trained policies utilizing privileged information (2).
- Transferring objectives across skills: Learning a new skill based on a set of previously trained skills, though each was developed with distinct objectives. For instance, transferring knowledge from grasping, picking, and placing tasks to facilitate learning skills like opening doors or drawers.
In both approaches, particular emphasis will be placed on using embodiment-agnostic, task-independent, multi-view, object-centric scene representations. These representations are anticipated to significantly enhance the efficiency and effectiveness of skill transfer.
Finally, generalized approaches for skill transfer will also be explored to further broaden the applicability and adaptability of this work.
Required skills
- MSc or PhD student in the final year, specializing in Machine Learning or Reinforcement Learning, ideally with a focus on Robotics. Publications in top-tier conferences are highly desirable and will strengthen the application.
- Strong background in deep learning.
- Advanced coding skills, particularly in PyTorch.
- Familiarity with robotics and robotic simulation environments is a plus.
References
1: Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges, N. Jaquier et al., arXiv:2311.18044.
2: Residual Reinforcement Learning from Demonstrations, M. Alakuijala, G. Dulac-Arnold, J. Mairal, J. Ponce, and C. Schmid, arXiv:2106.08050.
Application instructions
Please note that applicants must be registered students at a university or other academic institution and that this establishment will need to sign an 'Internship Convention' with NAVER LABS Europe before the student is accepted.
You can apply for this position online. Don't forget to upload your CV and cover letter before you submit. Incomplete applications will not be accepted.
About NAVER LABS
NAVER is the #1 Internet portal in Korea with activities that span a wide range of businesses including search, commerce, content, financial and cloud platforms.
NAVER LABS, co-located in Korea and France, is the organization dedicated to preparing NAVER’s future. NAVER LABS Europe is located in a spectacular setting in Grenoble, in the heart of the French Alps. Scientists at NAVER LABS Europe are empowered to pursue long-term research problems that, if successful, can have significant impact and transform NAVER. We take our ideas as far as research can to create the best technology of its kind. Active participation in the academic community and collaborations with world-class public research groups are, among others, important tools to achieve these goals. Teamwork, focus and persistence are important values for us.
NAVER LABS Europe is an equal opportunity employer.
Related Jobs
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
VISION
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.