- 5
- 2
- 1
- 1
Nicolas Duminy
9
Documents
Identifiants chercheurs
- nicolas-duminy
- 0000-0002-8360-6635
Présentation
Research & Development engineer at IMT Atlantique, Brest campus
===================================================================
I work as a supporting role for the researchers of the LUSSI department at IMT Atlantique since 2021.
I am deeply involved in the [Decion Deck consortium](https://www.decision-deck.org/project/), for which I helped release the 4.0 version of the Diviz software for Multi-Criteria Decision Aiding. Now I am currently working on different projects:
- [PyMCDA](https://gitlab.com/nduminy/pymcda): a new all-encompassing python library aiming at becoming the Multi-Criteria Decision Aiding toolbox for data scientists & engineers (supported by the Decision Deck consortium)
- A python library for community analysis which generates configurable and coherent dynamic temporal communities for benchmarking purposes (not open-source yet, publication in preparation)
- [ANR-PIL](http://www.anr-pil.org): a python data pipeline for the detection of echo chambers forming in Youtube comment sections (not open source yet, publication in preparation)
Previous positions
==================
2020: Self Employed
-------------------
Development of a virtual reality platform for Location Based Virtual Reality inside IMT Atlantique business incubator.
May - December 2019: Post-Doc at IMT Atlantique, Brest campus
-------------------------------------------------------------
Explorative Post-Doc on 3D printing as a service and Industry 4.0 inside the P4S team of the computer engineering department.
November 2018 - April 2019: R&D engineer at IMT Atlantique, Brest campus
----------------------------------------------------------------------------
Development and experimentations on the ABB YuMi industrial robot of the developmental robotics algorithms developed during my thesis.
Publications
- 4
- 4
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 8
- 4
- 3
- 2
- 2
- 1
- 1
- 6
- 5
- 4
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 2
- 1
- 1
- 4
- 1
- 1
|
Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task HierarchyApplied Sciences, 2021, 11 (3), pp.975. ⟨10.3390/app11030975⟩
Article dans une revue
hal-03118190v1
|
|
Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum LearningKI - Künstliche Intelligenz, 2021, 35 (81-90), ⟨10.1007/s13218-021-00708-8⟩
Article dans une revue
hal-03157219v1
|
|
Learning a set of interrelated tasks by using a succession of motor policies for a socially guided intrinsically motivated learnerFrontiers in Neurorobotics, 2019, ⟨10.3389/fnbot.2018.00087⟩
Article dans une revue
hal-02087995v1
|
|
Découverte et exploitation de la hiérarchie des tâches par motivation intrinsèqueRéunion "Apprentissage et Robotique", GDR ISIS; GDR Robotique, Jun 2020, Visioconférence, France
Communication dans un congrès
hal-02894956v2
|
|
Learning Sequences of Policies by using an Intrinsically Motivated Learner and a Task HierarchyWorkshop on Continual Unsupervised Sensorimotor Learning, ICDL-EpiRob 2018, Sep 2018, Tokyo, Japan
Communication dans un congrès
hal-01887073v1
|
|
Effects of social guidance on a robot learning sequences of policies in hierarchical learningSMC 2018 : IEEE International Conference on Systems, Man and Cybernetics, Oct 2018, Miyazaki, Japan. pp.3755 - 3760, ⟨10.1109/SMC.2018.00636⟩
Communication dans un congrès
hal-02066931v1
|
|
Learning a Set of Interrelated Tasks by Using Sequences of Motor Policies for a Strategic Intrinsically Motivated Learner2018 Second IEEE International Conference on Robotic Computing (IRC), Jan 2018, Laguna Hills, France. pp.288 - 291, ⟨10.1109/IRC.2018.00061⟩
Communication dans un congrès
hal-01869508v1
|
|
Strategic and interactive learning of a hierarchical set of tasks by the Poppy humanoid robotICDL-EpiRob 2016 : 6th Joint IEEE International Conference Developmental Learning and Epigenetic Robotics, Sep 2016, Cergy-Pontoise, France. pp.204 - 209, ⟨10.1109/DEVLRN.2016.7846820⟩
Communication dans un congrès
hal-01547074v1
|
|
Discovering and exploiting the task hierarchy to learn sequences of motor policies for a strategic and interactive robotComputer science. Université de Bretagne Sud, 2018. English. ⟨NNT : 2018LORIS513⟩
Thèse
tel-02280809v1
|