Hierarchical Multi-agent Reinforcement Learning for

il y a 3 semaines


Grenoble, France NAVER LABS Europe Temps plein

NAVER LABS Europe’s Action Group is focussed on enabling embodied agents to efficiently execute complex tasks and navigate in dynamic environments. Within the Optimization With Learning (OWL) team of the Action group, the intern will focus on the optimization of a fleet of robots. Those robots must perform a set of tasks associated with specific locations, and navigate a constrained environment, avoiding one another, to complete their tasks.

This problem is decomposed into a bi-level optimization problem. At the upper level, the tasks and necessary resources are assigned to robots. At the lower level, a multi-agent path finding problem (MAPF) is solved to optimize the displacement of the robots, avoiding collision. The objective of the internship is to propose a multi-agent reinforcement learning (MARL) approach to optimize the assignment and scheduling of the tasks, given paths produced by a MAPF algorithm. Formalizing such a problem for MARL requires tackling off-beat actions [Qiu et al. 2022], i.e., asynchronously executed temporally varying stochastic actions stemming from the actual dynamics of the robots.

Similar problems are often addressed in the literature with a proxy measure and a centralized controller, but recent results suggest MARL as a possible efficient approach for this problem [Krnjaic et al. 2023].

[Krnjaic et al. 2023] Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers. Aleksandar Krnjaic, Raul D. Steleac, Jonathan D. Thomas, Georgios Papoudakis, Lukas Schäfer, Andrew Wing Keung To, Kuan-Ho Lao, Murat Cubuktepe, Matthew Haley, Peter Börsting, Stefano V. Albrecht. arXiv: 2212.11498v2

[Qiu et al. 2022] Off-Beat Multi-Agent Reinforcement Learning. Wei Qiu, Weixun Wang, Rundong Wang, Bo An, Yujing Hu, Svetlana Obraztsova, Zinovi Rabinovich, Jianye Hao, Yingfeng Chen, Changjie Fan. AAMAS 2023 Extended Abstract. arXiv: 2205.13718.

**Supervisors**: Vassilissa Lehoux and Tomi Silander

Required skills
- Master or Ph.D. student in machine learning and/or combinatorial optimization
- Good development skills (Python is preferred), experience in machine learning frameworks
- Knowledge in reinforcement learning, and if possible combinatorial optimization

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.

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.



  • Grenoble, France Université Grenoble Alpes Temps plein

    **Geometrie de l'information et apprentissage par renforcement en distribution // Information Geometry Aware Distributional Reinforcement Learning**: - Réf **ABG-124282** **ADUM-57750** - Sujet de Thèse- 30/05/2024- Université Grenoble Alpes- Lieu de travail- Grenoble Cedex 9 - France- Intitulé du sujet- Geometrie de l'information et apprentissage par...


  • Grenoble, France NAVER LABS Europe Temps plein

    NAVER LABS is the R&D arm of NAVER, Korea’s leading internet company. Its world-class researchers in Korea and Europe create new connections between people, machines and spaces by advancing technology in AI and robotics. NAVER LABS Europe is the biggest industrial research lab in AI in France and conducts advanced research in Machine Learning, Computer...


  • Grenoble, France GreenWaves Technologies Temps plein

    **Context**: GreenWaves is a fabless semiconductor company founded in 2014 and based in Grenoble, France. We design and market ultra low power processors for energy constrained products such as hearables, wearables, IoT & medical monitoring products. GreenWaves’ system-on-chips enable companies to develop and bring to market products with new to world...

  • Senior Low Power Dft Engineer

    il y a 4 semaines


    Grenoble, France GreenWaves Technologies Temps plein

    **Context**: GreenWaves is a fabless semiconductor company founded in 2014 and based in Grenoble, France. We design and market ultra low power processors for energy constrained products such as hearables, wearables, IoT & medical monitoring products. GreenWaves’ system-on-chips enable companies to develop and bring to market products with new to world...


  • Grenoble, France TrailStone Group Temps plein

    **Grenoble Office | On-site Working | Full-time Role** **About the Role** Trailstone seeks to advance the scientific frontiers of forecasting power production for wind and solar parks. As a Quantitative Researcher working at the intersection of deep learning and meteorology, you will play a central role in our mission of making sustainable energy...


  • Grenoble, France GreenWaves Technologies Temps plein

    **Context**: GreenWaves is a fabless semiconductor company founded in 2014 and based in Grenoble, France. We design and market ultra low power processors for energy constrained products such as hearables, wearables, IoT & medical monitoring products. GreenWaves’ system-on-chips enable companies to develop and bring to market products with new to world...

  • Senior Dsp Engineer

    il y a 1 mois


    Grenoble, France GreenWaves Technologies Temps plein

    **Context**: GreenWaves is a fabless semiconductor company founded in 2014 and based in Grenoble, France. We design and market ultra low power processors for energy constrained products such as hearables, wearables, IoT & medical monitoring products. GreenWaves’ system-on-chips enable companies to develop and bring to market products with new to world...


  • Grenoble, France NAVER LABS Europe Temps plein

    Automatic speech recognition (ASR) systems have seen substantial improvements in the past decade, in particular with the advent of Self-supervised learning speech models; however, ASR systems do not recognize the speech of everyone equally well. Recent research shows that bias exists against different types of speech, including non-native and regional...


  • Grenoble, France Nagarro Temps plein

    Company Description We're Nagarro. We are a digital product engineering company that is scaling in a big way! We build products, services, and experiences that inspire, excite, and delight. We work at scale — across all devices and digital mediums, and our people exist everywhere in the world (20,000+ experts across 30 countries, to be exact). Our work...


  • Grenoble, France ESRF Temps plein

    Context & Job description Structural Biology is one of the most important family of techniques at the ESRF, both for academic and industrial users, with state-of-the-art instruments including the upgraded ID29 beamline for time-resolved serial crystallography. You will join the team of scientists and software engineers working on the applications and...

  • Director, Delivery

    il y a 1 mois


    Grenoble, France Nagarro Temps plein

    Company Description We're Nagarro. We are a digital product engineering company that is scaling in a big way! We build products, services, and experiences that inspire, excite, and delight. We work at scale — across all devices and digital mediums, and our people exist everywhere in the world (17,000+ experts across 30 countries, to be exact). Our work...


  • Grenoble, France Nagarro Temps plein

    Company Description We're Nagarro. We are a digital product engineering company that is scaling in a big way! We build products, services, and experiences that inspire, excite, and delight. We work at scale — across all devices and digital mediums, and our people exist everywhere in the world (20,000+ experts across 30 countries, to be exact). Our work...


  • Grenoble, France Université Grenoble Alpes Temps plein

    **Le développement du pouvoir genré // The development of gendered power**: - Réf - **ABG-113767** **ADUM-49305** - Sujet de Thèse- 25/04/2023- Contrat doctoral- Université Grenoble Alpes- Lieu de travail- Grenoble Cedex 9 - France- Intitulé du sujet- Le développement du pouvoir genré // The development of gendered power- Mots clés- Enfant, genre,...


  • Grenoble, France ESRF Temps plein

    Context & Job description You will develop advanced X-ray imaging workflows accessible and usable by the biological user community. In particular, you will enhance high resolution cryo tomography for the combined use of X-rays and electrons. You will develop sample mounting systems and automated image registration to perform correlative multi-modal...


  • Grenoble, France Cea Temps plein

    As part of these activities, we are looking for a research engineer to strengthen the team and carry out research and development work in the area of resource allocation, orchestration protocols and optimization for future wireless communication systems. These systems will include communication, computing and storage resources, as part of edge computing...


  • Grenoble, Auvergne-Rhône-Alpes, France Cea Temps plein

    As part of these activities, we are looking for a research engineer to strengthen the team and carry out research and development work in the area of resource allocation, orchestration protocols and optimization for future wireless communication systems. These systems will include communication, computing and storage resources, as part of edge computing...


  • Grenoble, France CEA - Commissariat à l'Energie Atomique Temps plein

    **Domaine**: Mathématiques, information scientifique, logiciel **Contrat**: Stage **Intitulé de l'offre**: Challenges in time series modelling: a study applied to blood pressure estimation from PPG data **Sujet de stage**: Our aim is monitoring cardiovascular health, and in particular blood pressure. Based on the technology available in our department,...


  • Grenoble, France GreenWaves Technologies Temps plein

    **Context**: GreenWaves Technologies is a fabless semiconductor start-up with headquarters in Grenoble, France and offices in Bologna (Italy) and Shanghai (China). We design powerful, highly efficient and easy to program ultra-low-power AI+DSP processors based on RISC-V. GreenWaves’ mission is to enable the sensing edge wherever it might get to. We started...


  • Grenoble, France ESRF Temps plein

    Context & Job description Scanning X-ray techniques are among the most widely used at ESRF, notably for spectroscopy applications, providing rich spatial and elemental information on a large variety of samples (cultural heritage, batteries, metallurgy, semi-conductors, etc..). The ESRF ‘Extremely Brilliant Source’ upgrade has led to an increase in...

  • Agent de Restauration

    il y a 1 mois


    Grenoble, France Easyhiring for WHC_HU_MJC Temps plein

    L'agence d'emploi EasyHiring recherche un(e) Agent de restauration à Grenoble pour nos partenaires. Votre spécialité consiste à préparer et/ou à participer à la préparation des repas dans les conditions d’hygiène réglementaires (cuisinier/agent polyvalent), à assurer des prestations liées au service en salle, à table, au bar, à l’accueil...