EN FR
EN FR


Section: Partnerships and Cooperations

International Initiatives

Inria International Partners

  • Luis Montesano, University of Zaragoza, Spain. Manuel Lopes collaborated with Luis Montesano on several topics. Recently on active learning approaches for grasping point learning [103] and clustering activities.

  • Francisco Melo Instituto Superior Técnico, Portugal. Manuel Lopes collaborated with Francisco Melo on the development of active learning for inverse reinforcement learning. Recent developments consider the extension to more cues available to the learner and sampling complexity on the algorithm.

  • José Santos-Victor, Instituto Superior Técnico, Portugal. Manuel Lopes collaborated with José Santos-Victor on the extension of affordances models to higher levels of representations, e.g. relational models.

  • Maya Cakmak, Andrea Thomaz, Georgia Tech, USA. Manuel Lopes collaborated with Maya Cakmak on the development of optimal teaching algorithms for sequential decision problems (modeled as markov decision processes). The algorithm provides optimal demonstrations for systems that learn using inverse reinforcement learning. The joint work considers not only the algorithmic aspects but also a comparison with human behavior and the possibility of using insights from the algorithm to elicit better teaching behavior on humans [32] .

  • Marc Toussaint, Tobias Lang, Free University of Berlin, Germany. Manuel Lopes and Pierre-Yves Oudeyer are collaborating with FUB in the unification of exploration algorithms based on intrinsic motivation with methods for exploration in reinforcement learning such as R max . We intend to develop a general framework for exploration in non-stationary domains [46] . Another project consider how to learn efficient representation for robotic hierarchical planning [44] .

  • Todd Hester and Peter Stone, University of Texas, USA ( 2012 - )

    Peter Stone is a leading expert on reinforcement learning applied to real robots ( he won the RobotCup competition several times) and to multi-agent problems. We started this collaboration by introducing a new method to automatically select the best exploration strategy to use in a particular problem [42] . Future directions of the collaboration will include ad-hoc teams, exploration in continuous space and human-guided machine learning.

  • Jacqueline Gottlieb and Adrien Baranes, Columbia University, New-York, US. Pierre-Yves Oudeyer and Manuel Lopes continued a collaboration with Jacqueline Gottlied, neuroscientist at Columbia University and specialist of visual attention and exploration in monkeys, and Adrien Baranes, postdoc in Gottlieb's lab and previously working in Flowers team. An experimental set-up with brain imaging and behavioural observations of monkeys, and made to evaluate new families of computational models of visual attention and exploration (some of which developped in the team around the concept of intrinsic motivation) is being elaborated.

  • Louis ten Bosch, Radboud University, The Netherlands. Pierre-Yves Oudeyer and David Filliat continued to work with Louis ten Bosch on the modelling of multimodal language acquisition using techniques based on Non-Negative Matrix Factorization. We showed that these techniques can allow a robot to discover audio-video invariants starting from a continuous unlabelled and unsegmented flow of low-level auditory and visual stimuli. A journal article is in preparation.

  • Britta Wrede, Katharina Rohlfing, Jochen Steil and Sebastian Wrede, Bielefeld University, Germany, Jun Tani KAIST, South Korea. Pierre-Yves Oudeyer collaborated with Wrede, Rohlfing, Steil, Wrede and Tani on the elaboration of a novel conceptual vision of teleoogical language and action development in robots. This led to the publication of a joint workshop article [64] .

  • Michael A. Arbib, University of Southern California (Los Angeles, USA). Clément Moulin-Frier is continuing his collaborative work with Michael Arbib since his 6-month visit at USC in 2009. See the section entitled “Recognizing speech in a novel accent: the Motor Theory of Speech Perception reframed” for more information.

  • Paul Vogt (Tillburg University, The Netherlands), Linda Smith (Indiana University, Bloomington, US), Aslo Ozyurek (Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands), Tony Belpaeme (University of Plymouth, UK). Pierre-Yves Oudeyer began collaboration with partners of the NWO SCMSC project to set up a research network on modeling of social cognition and symbolic communication.

  • Michael Gienger from Honda Research Institute Europe. Alexander Gepperth collaborated with Principal Scientist Dr.Michael Gienger from Honda Research Institute Europe GmbH about robotic grasping: this activity will result in a jointly supervised internship ("stage de fine d'études") and a publication.

  • Ursula Korner from Honda Research Institute Europe. Alexander Gepperth collaborated with Dr. Usula Körner of Honda Research Institute Europe GmbH, Offenbach (Germany), on the topic of biologically inspired learning architectures for visual categorization of behaviorally relevant entities. This work is intended to be summitted to the International Conference on Development and Learning, as well as the journal "Frontiers in Cognitive Systems".

  • Michael Garcia Ortiz, Laboratory for Cognitive Robotics (CoR-Lab) in Bielefeld, Germany. Alexander Gepperth collaborated with Michael Garcia Ortiz, a PhD student from the Laboratory for Cognitive Robotics (CoR-Lab) in Bielefeld, Germany, on the exploitation of scene context for object detection in intelligent vehicles. This collaboration resulted in the submission of a journal publication to the journal ”Neurocomputing”.

  • Martha White and Richard Sutton from the University of Alberta, Canada. Thomas Degris collaborated with Martha White and Richard Sutton on the paper “Off-Policy Actor–Critic” [38] .

  • Patrick Pilarski and Richard Sutton from the University of Alberta (Canada). Thomas Degris collaborated with Patrick Pilarski on the following papers: “Model-Free Reinforcement Learning with Continuous Action in Practice” [37] , “Apprentissage par Renforcement sans Modèle et avec Action Continue” [65] , “Dynamic Switching and Real-time Machine Learning for Improved Human Control of Assistive Biomedical Robots” [57] , “Towards Prediction-Based Prosthetic Control” [58] , and “Prediction and Anticipation for Adaptive Artificial Limbs” [27] .

  • Joseph Modayil from the University of Alberta, Canada. Thomas Degris collaborated with Joseph Modayil on the following paper: “Scaling-up Knowledge for a Cognizant Robot” [35] .

  • Ashique Rupam Mahmood from the University of Alberta, Canada. Thomas Degris collaborated with Ashique Rupam Mahmood on the following paper: “Tuning-Free Step-Size Adaptation” [50] .