Search

International audience; In this paper we present a new approach for semantic recognition in the context of robotics. When a robot evolves in its environment, it gets 3D information given either by its sensors or by its own motion through 3D reconstruction. Our approach uses (i) 3D-coherent synthesis of scene observations and (ii) mix them in a multi-view framework for 3D labeling. (iii) This is efficient locally (for 2D semantic segmentation) and globally (for 3D structure labeling). This allows to add semantics to the observed scene that goes beyond simple image classification, as shown on challenging datasets such as SUNRGBD or the 3DRMS Reconstruction Challenge.

We propose a depth map inference system from monocular videos based on a novel dataset for navigation that mimics aerial footage from gimbal stabilized monocular camera in rigid scenes. Unlike most navigation datasets, the lack of rotation implies an easier structure from motion problem which can be leveraged for different kinds of tasks such as depth inference and obstacle avoidance. We also propose an architecture for end-to-end depth inference with a fully convolutional network. Results show that although tied to camera inner parameters, the problem is locally solvable and leads to good quality depth prediction.

International audience; Some studies hypothesize a strong interdependence between speech and tool use development in the first two years of life. To help understand the underlying mechanisms, we present the first robotic model learning both speech and tool use from scratch. It focuses on the role of one important form of body babbling where exploration is directed towards self-generated goals in free play, combined with imitation learning of a contingent caregiver. This model does not assume capabilities for complex sequencing and combinatorial planning which are often considered necessary for tool use. Yet, we show that the mechanisms in this model allow a learner to progressively discover how to grab objects with the hand, how to use objects as tools to reach further objects, how to produce vocal sounds, and how to leverage these vocal sounds to use a caregiver as a social tool to retrieve objects. Also, the discovery that certain sounds can be used as a social tool further guides vocal learning. This model predicts that the grounded exploration of objects in a social interaction scenario should accelerate infant vocal learning of accurate sounds for these objects' names.

International audience; The schooling of children with autism spectrum disorder is a challenge that relies on all stakeholders (families, schools, and medical-social professionals). In many countries, the Individualized Education Plan (IEP) is a monitoring tool of the schooling process, implemented by the aforementioned stakeholders, but they face several barriers to the co-education process. The CoEd web app was designed using participatory methods in France, with interactive services for the children's follow-up and the three-way collaboration. CoEd applicability was assessed in Belgian cultural context (Walloon territory), as they experiences similar issues.The results showed comparable results between the two countries. The Belgian audience appreciated CoEd and would be ready to use it in real conditions, as is currently the case in France. Thus, this participatory design work developed a tool that meets the needs expressed by the French participants and those of stakeholders beyond French borders.; La scolarisation des enfants atteints de troubles du spectre autistique est un défi qui repose sur l'ensemble des acteurs (familles, écoles et professionnels médico-sociaux). Dans de nombreux pays, le plan d'éducation individualisé (PEI) est un outil de suivi du processus de scolarisation, mis en œuvre par les parties prenantes susmentionnées, mais celles-ci se heurtent à plusieurs obstacles dans le processus de coéducation. L'application web CoEd a été conçue en utilisant des méthodes participatives en France, avec des services interactifs pour le suivi des enfants et la collaboration tripartite. L'applicabilité de CoEd a été évaluée dans le contexte culturel belge (territoire wallon), étant donné que les deux pays connaissent des problèmes similaires. Le public belge a apprécié CoEd et serait prêt à l'utiliser dans des conditions réelles, comme c'est actuellement le cas en France. Ainsi, ce travail de conception participative a permis de développer un outil qui répond aux besoins exprimés par les participants français et à ceux des acteurs au-delà des frontières françaises.Traduit avec www.DeepL.com/Translator (version gratuite)

International audience

One of the fundamental goals of Artificial Intelligence (ai) is to design embodied autonomous agents that can evolve in various environments, perform a multitude of tasks and interact with humans. To this end, ai researchers employ various approaches, with two primary methods standing out: developmental robotics and standard ai paradigms. While developmental robotics models agents’ cognitive development in simplified environments, standard AI paradigms focus on algorithmic contributions in precise and technical benchmarks. In this thesis, we extend upon recent calls to bridge these two fields and investigate the role of cultural conventions in the development of artificial agents using state-of-the-art ai algorithms. This research leverages work from developmental psychology and focuses on two crucial aspects of human development, namely autotelic and social learning. The former enables agents to form open-ended repertoires of skills by inventing and pursuing their own goals while the latter enables them to communicate, cooperate, teach, and organize their thoughts. Our contributions are organized around two fundamental scientific questions: 1) the formation of cultural conventions within populations of artificial agents, and 2) the exploitation of cultural conventions in their cognitive development. The first part of this manuscript deals with the formation of cultural conventions. It builds on recent studies in the field of emergent communication to propose two computational studies. The first one investigates the formation of cultural conventions in the ecological context where artificial agents communicate via a graphical sensory-motor channel. The second one draws inspiration from experimental semiotics and studies the emergence of communication in the architect-builder problem: a novel interactive learning paradigm where agents have asymmetries of information and affordances which makes the application of standard Multi-Agent Reinforcement Learning impossible. The second part focuses on the exploitation of cultural conventions. Inspired by the pioneering work of Vygotsky and other psychologists we first introduce the Vygotskian Autotelic ai Framework. This framework enables Reinforcement Learning agents to internalize social interactions in order to transform their cognitive abilities enabling them to form abstract representations, achieve systematic generalization, and creatively explore their environment. Following this conceptual contribution, we propose two computational studies. The first one explores the role of inductive biases in the language grounding problem where agents need to align their physical experience of the world with linguistic inputs provided by social partners. Our final computational contribution introduces the imagine agent: a Vygotskian autotelic agent that converts linguistic descriptions given by a social partner into targetable goals. imagine leverages language productivity and systematic generalization to grow an open-ended repertoire of skills in a creative way.; L'un des objectifs fondamentaux de l'Intelligence Artificielle (IA) est de concevoir des agents autonomes incarnés capables d'évoluer dans divers environnements, d'accomplir une multitude de tâches et d'interagir avec les humains. À cette fin, les chercheurs en IA utilisent différentes approches, avec deux méthodes principales se distinguant : la robotique développementale et les paradigmes d'IA standard. Alors que la robotique développementale modélise le développement cognitif des agents dans des environnements simplifiés, les paradigmes d'IA standard se concentrent sur les contributions algorithmiques dans des benchmarks précis et techniques. Dans cette thèse, nous prolongeons les appels récents à combler ces deux domaines et examinons le rôle des conventions culturelles dans le développement d'agents artificiels en utilisant des algorithmes d'IA de pointe.Cette recherche s'appuie sur le travail de la psychologie du développement et se concentre sur deux aspects cruciaux du développement humain, à savoir l'apprentissage autotélique et social. Le premier permet aux agents de former des répertoires de compétences ouverts en inventant et en poursuivant leurs propres objectifs, tandis que le second leur permet de communiquer, de coopérer, d'enseigner et d'organiser leurs pensées.Nos contributions sont organisées autour de deux questions scientifiques fondamentales : 1) la formation de conventions culturelles au sein de populations d'agents artificiels, et 2) l'exploitation de conventions culturelles dans leur développement cognitif.La première partie de ce manuscrit traite de la formation de conventions culturelles. Elle s'appuie sur des études récentes dans le domaine de la communication émergente pour proposer deux études computationnelles. La première étudie la formation de conventions culturelles dans le contexte écologique où les agents artificiels communiquent via un canal sensorimoteur graphique. La seconde s'inspire de la sémiotique expérimentale et étudie l'émergence de la communication dans le problème de l'architecte-constructeur : un nouveau paradigme d'apprentissage interactif où les agents ont des asymétries d'information et des affordances qui rendent l'application de l'apprentissage par renforcement multi-agent standard impossible.La seconde partie se concentre sur l'exploitation de conventions culturelles. Inspirés par les travaux pionniers de Vygotsky et d'autres psychologues, nous introduisons d'abord le framework Vygotskien d'IA autotélique. Ce framework permet aux agents d'apprentissage par renforcement d'intérioriser les interactions sociales afin de transformer leurs capacités cognitives, leur permettant de former des représentations abstraites, d'atteindre une généralisation systématique et d'explorer leur environnement de manière créative. À la suite de cette contribution conceptuelle, nous proposons deux études computationnelles. La première explore le rôle des biais inductifs dans le problème d'ancrage de langage où les agents doivent aligner leur expérience physique du monde avec les entrées linguistiques fournies par des partenaires sociaux. Notre dernière contribution computationnelle introduit l'agent IMAGINE : un agent autotélique Vygotskien qui convertit les descriptions linguistiques données par un partenaire social en objectifs atteignables. Imagine tire parti de la productivité linguistique et de la généralisation systématique pour développer de manière créative un répertoire de compétences ouvert.

National audience; Introduction. – With a prevalence of 2.3% among French schoolchildren aged 6 to 16, giftedness represents a challenge in child psychiatry (Delaubier, 2002). Dys-synchronies can appear in the different domains of intelligence, associated with eclectic symptoms: hypersensitivity, anxiety, depression, attention deficit disorder with or without hyperactivity, oppositional disorder as well as conduct disorders. The psychological assessment can constitute an opportunity to identify and evaluate giftedness functioning in order to advise an adapted treatment in the guidance of these children and teenagers, and to guarantee them the most harmonious global development.Method. – The method used was that of a case study. was received within clinical research carried out at the University of Bordeaux for the realization of a psychological assessment. The objective of the assessment was to investigate and understand the polymorphic anxiety domain but also the impossibility for Minerva to attend middle school, with the result that she was home schooled with the National Center for Distance Learning (CNED). Over two half-days, we were able to successively carry out the anamnestic interview, a semi-structured interview, the K-SADS, the evaluation of cognitive functioning with the WISC-V, various projective tests such as the TAT, the Rorschach test, a drawing of a man and a family, as well as various scales in self and hetero-evaluation.Results. – The K-SADS clarified the psychopathological situation as well as the family, social and school impact of this invasive case of anxiety. The results of the WISC-V showed an intellectual potential between 117 and 129, with areas of high efficiency for the Verbal Comprehension Index (VCI = 146) and the Working Memory Index (WMI = 122). The profile, although not reaching the recommended 130 in global IQ, is consistent with high intellectual potential when the performance is impacted by the situation of parasitic anxiety and a sedative medication. The projective tests as well as the drawings of the man and the family, demonstrated the extent of the considerable rigid defense mechanisms and of avoidance, but also of the hyper investment of the intellectualization processes.Conclusion. – The screening of high intellectual potential represents a clinical challenge in view of the lack of diagnostic recommendations as well as the disparity of information accumulated in research on their characteristics. The holistic approach of the psychological assessment appears to be a solution allowing to situate the individual’s psychic functioning in a constitutive zone of the "high intellectual potential" profile, which should also be at the service of the global therapeutic management.; Introduction. – La prévalence du haut potentiel intellectuel (HPI) chez les enfants français scolarisés entre 6 et 16 ans est estimée à 2,3 %, représentant ainsi un défi majeur en pédopsychiatrie (Delaubier, 2002). Des décalages peuvent se manifester dans les différents domaines de l’intelligence, associés à des symptômes variés : hypersensibilité, anxiété, dépression, trouble déficitaire de l’attention avec ou sans hyperactivité, trouble oppositionnel, et troubles des conduites. Le bilan psychologique peut constituer l’opportunité de détecter ainsi que d’évaluer le fonctionnement HPI afin de proposer un suivi adapté pour ces enfants et adolescents, dans le but de pouvoir assurer l’harmonie de leur développement global.Méthode. – La méthode retenue est celle de l’étude de cas. Minerva, 14 ans et 11 mois, fut accueillie ausein d’une recherche clinique menée à l’université de Bordeaux pour la réalisation d’un bilan psychologique. L’objectif du bilan était d’investiguer ainsi que comprendre la scène anxieuse polymorphe mais aussi l’impossibilité de se rendre au collège, ayant pour conséquence la scolarisation à domicile via le Centre National d’Enseignement a` Distance (CNED). Sur deux demi-journées, nous avons pu successivement faire l’entretien anamnestique, l’entretien semi-structuré K-SADS, l’évaluation du fonctionnement cognitif avec la WISC-V, différents tests projectifs comme le TAT, le test de Rorschach, un dessin du bonhomme et de la famille, ainsi que différentes échelles en auto- et hétéro-évaluation.Résultats. – La K-SADS a permis de clarifier la situation psychopathologique ainsi que l’impact familial, social et scolaire de cette scène anxieuse invasive. Les résultats au WISC-V ont mis en évidence un potentiel intellectuel compris entre 117 et 129, avec des zones d’efficience haute pour l’Indice de Compréhension Verbale (ICV = 146) et l’Indice de Mémoire de Travail (IMT = 122). Le profil, bien que n’atteignant pas les 130 recommandés en QI global, s’inscrit dans celui d’un haut potentiel, avec une performance impactée par la situation d’une anxiété parasite et d’une médication interférente. Les tests projectifs, ainsi que les dessins du bonhomme et de la famille, ont démontré l’étendue de la massivité des mécanismes de défenses rigides et d’évitement, mais aussi de l’hyperinvestissement du processus d’intellectualisation.Conclusion. – Le dépistage du haut potentiel intellectuel représente un défi clinique face aux manques de recommandations diagnostiques ainsi qu’à la disparité d’informations cumulées en recherche sur leurs caractéristiques. L’approche holistique du bilan psychologique apparaît néanmoins comme une solution permettant de situer les fonctionnements psychiques de l’individu dans une zone constitutive du profil de « haut potentiel intellectuel », se devant aussi d’être au service de la prise en charge thérapeutique globale.

International audience; In the context of sensory or higher-level cognitive processing, we present a recurrent neural network model, similar to the popular dynamic neural field (DNF) model, for performing approximate probabilistic computations. The model is biologically plausible, avoids impractical schemes such as log-encoding and noise assumptions, and is well-suited for working in stacked hierarchies. By Lyapunov analysis, we make it very plausible that the model computes the maximum a posteriori (MAP) estimate given a certain input that may be corrupted by noise. Key points of the model are its capability to learn the required posterior distributions and represent them in its lateral weights, the interpretation of stable neural activities as MAP estimates, and of latency as the probability associated with those estimates. We demonstrate for in simple experiments that learning of posterior distributions is feasible and results in correct MAP estimates. Furthermore, a pre-activation of field sites can modify attractor states when the data model is ambiguous, effectively providing an approximate implementation of Bayesian inference.

International audience; We propose an incremental, highly parallelizable, and constant-time complexity neural learning architecture for multi-class classification (and regression) problems that remains resource-efficient even when the number of input dimensions is very high (≥ 1000). This so-called projection-prediction (PROPRE) architecture is strongly inspired by biological information processing in that it uses a prototype-based, topologically organized hidden layer trained with the SOM learning rule that updates hidden layer weights whenever an error occurs. The SOM learning adapts only the weights of localized neural sub-populations that are similar to the input, which explicitly avoids the catastrophic forgetting effect of MLPs in case new input statistics are presented. The readout layer applies linear regression to hidden layer activities subjected to a transfer function, making the whole system capable of representing strongly non-linear decision boundaries. The resource-efficiency of the algorithm stems from the fact of approximating similarity in the input space by proximity in the SOM layer due to the topological SOM projection property. This avoids the storage of inter-cluster distances (quadratic in number of hidden layer) or input space covariance matrices (quadratic in input dimensions) as K-means, RBF or LWPR would have to do. Tests on the popular MNIST handwritten digit benchmark show that the algorithm compares favorably to state-of-the-art results, and parallelizability is demonstrated by analyzing the efficiency of a parallel GPU implementation of the architecture.

International audience; PROPRE is a generic and cortically inspired framework that provides online input/output relationship learning. The input data flow is projected on a self-organizing map that provides an internal representation of the current stimulus. From this representation, the system predicts the value of the output target. A predictability measure, based on the monitoring of the prediction quality, modulates the projection learning so that to favor learning of representations that are helpful to predict the output. In this article, we study PROPRE when the input/output relationship is only defined in a small subspace of the input space, that we define as a partially learnable environment. This problem, which is not typical of the machine learning field, is however crucial for the robotic developmental field. Indeed, robots face high dimensional sensory-motor environments where large areas of these sensory-motor spaces are not learnable since a motor action cannot have a consequence on every perception each time. We show that the use of the predictability measure in PROPRE leads to an autonomous gathering of local representations where the input data are related to the output value, thus providing good classification performance as the system will learn the input/output function only where it is defined.

International audience

Immersive technologies (imT) is claimed to have many benefits for learning, such as the ability to optimize learners' cognitive load (CL) as well as their curiosity states (intrinsic motivation) (CS-IM). From 2802 studies, we selected only 31 studies with a reliable study-design for investigating the impact of Virtual Reality (VR) and/or Augmented Reality (AR) on learning performance with respect to measurements of cognitive load and/or curiosity state. To this end, we built an analytical gird for probing positive, negative, null, or uninterpretable relationships between the learning performance and CL or CS-IM measures. The 24 studies focusing on CL show that the imT benefit for learning depends on technology with CL advantage for AR and with CL disadvantage for VR. For the 15 studies with a focus on CS-IM, the results are inconclusive and inconsistent due to large methodological differences in measuring this facet of the learning experience. Of the 8 studies investigating both CL and CS-IM, very few studies documented causal links between these two learning-related constructs, and the reported results were contradictory. The role of variables such as the type of knowledge taught, the type of learning, or the level of prior knowledge of the learners is examined. However, these variables did not yield significant insight into the relationships between the imT-learning performance and the learner experience in terms of CL and/or CS-IM. Recommendations for future research to address the identified gaps are provided for advancing the field of imT for learning. Keywords (from the imposed list) • Adult learning • Augmented and virtual reality • Media in education • Post-secondary education • Evaluation methodologies

International audience; Self-organizing map (SOM) is a powerful paradigm that is extensively applied for clustering and visualization purpose. It is also used for regression learning, especially in robotics, thanks to its ability to provide a topological projection of high dimensional non linear data. In this case, data extracted from the SOM are usually restricted to the best matching unit (BMU), which is the usual way to use SOM for classification , where class labels are attached to individual neurons. In this article, we investigate the influence of considering more information from the SOM than just the BMU when performing regression. For this purpose , we quantitatively study several output functions for the SOM, when using these data as input of a linear regression, and find that the use of additional activities to the BMU can strongly improve regression performance. Thus, we propose an unified and generic framework that embraces a large spectrum of models from the traditional way to use SOM, with the best matching unit as output, to models related to the radial basis function network paradigm, when using local receptive field as output.

In this article, we present some preliminary work on integrating an artificial curiosity mechanism in PROPRE, a generic and modular neural architecture, to obtain online, open-ended and active learning of a sensory-motor space, where large areas can be unlearnable. PROPRE consists of the combination of the projection of the input motor flow, using a self-organizing map, with the regression of the sensory output flow from this projection representation, using a linear regression. The main feature of PROPRE is the use of a predictability module that provides an interestingness measure for the current motor stimulus depending on a simple evaluation of the sensory prediction quality. This measure modulates the projection learning so that to favor the representations that predict the output better than a local average. Especially, this leads to the learning of local representations where an input/output relationship is defined [1]. In this article, we propose an artificial curiosity mechanism based on the monitoring of learning progress, as proposed in [2], in the neighborhood of each local representation. Thus, PROPRE simultaneously learns interesting representations of the input flow (depending on their capacities to predict the output) and explores actively this input space where the learning progress is the higher. We illustrate our architecture on the learning of a direct model of an arm whose hand can only be perceived in a restricted visual space. The modulation of the projection learning leads to a better performance and the use of the curiosity mechanism provides quicker learning and even improves the final performance.

International audience; PROPRE is a generic and modular neural learning paradigm that autonomously extracts meaningful concepts of multimodal data flows driven by predictability across modalities in an unsupervised, incremental and online way. For that purpose, PROPRE consists of the combination of projection and prediction. Firstly, each data flow is topologically projected with a self-organizing map, largely inspired from the Kohonen model. Secondly, each projection is predicted by each other map activities, by mean of linear regressions. The main originality of PROPRE is the use of a simple and generic predictability measure that compares predicted and real activities for each modal stream. This measure drives the corresponding projection learning to favor the mapping of predictable stimuli across modalities at the system level (i.e. that their predictability measure overcomes some threshold). This predictability measure acts as a self-evaluation module that tends to bias the representations extracted by the system so that to improve their correlations across modalities. We already showed that this modulation mechanism is able to bootstrap representation extraction from previously learned representations with artificial multimodal data related to basic robotic behaviors and improves performance of the system for classification of visual data within a supervised learning context. In this article, we improve the self-evaluation module of PROPRE, by introducing a sliding threshold, and apply it to the unsupervised classification of gestures caught from two time- of-flight (ToF) cameras. In this context, we illustrate that the modulation mechanism is still useful although less efficient than purely supervised learning.

International audience; PROPRE is a generic and modular unsupervised neural learning paradigm that extracts meaningful concepts of multimodal data flows based on predictability across modalities. It consists on the combination of three modules. First, a topological projection of each data flow on a self-organizing map. Second, a decentralized prediction of each projection activity from each others map activities. Third, a predictability measure that compares predicted and real activities. This measure is used to modulate the projection learning so that to favor the mapping of predictable stimuli across modalities. In this article, we use Kohonen map for the projection module, linear regression for the prediction one and we propose multiple generic predictability measures. We illustrate the properties and performances of PROPRE paradigm on a challenging supervised classification task of visual pedestrian data. The modulation of the projection learning by the predictability measure improves significantly classification performances of the system independently of the measure used. Moreover, PROPRE provides a combination of interesting functional properties, such as a dynamical adaptation to input statistic variations, that is rarely available in other machine learning algorithms.

International audience; PROPRE is a generic and semi-supervised neural learning paradigm that extracts meaningful concepts of multimodal data flows based on predictability across modalities. It consists on the combination of two computational paradigms. First, a topological projection of each data flow on a self-organizing map (SOM) to reduce input dimension. Second, each SOM activity is used to predict activities in all other SOMs. Predictability measure, that compares predicted and real activities, is used to modulate the SOM learning to favor mutually predictable stimuli. In this article, we study PROPRE applied to a classical visual pedestrian data classification task. The SOM learning modulation introduced in PROPRE improves significantly classification performance.

International audience; In recent years, many psycho-educational technologies were studied to address the school-related difficulties encountered by students with autism spectrum disorder (ASD). However, most of them remain individual-centered and do not consider the social environment. To fill this gap, this study reports on the user-centered design of a web-based support tool, which aims to support communication and coordination between parents, school staff, and health professionals of middle and high school students with ASD, in the context of elaborating, implementing, and following an Individualized Education Plan (IEP). The study followed a two-step design process: 1) a need analysis for identifying information domains deemed important by the stakeholders; 2) through a participative iterative design process, a panel of professionals and parents provided ideas and feedback on the design, which was integrated into subsequent prototype versions of the "ToGather" app.; Ces dernières années, de nombreuses technologies psycho-éducatives ont été étudiées pour répondre aux difficultés scolaires rencontrées par les élèves avec trouble du spectre autistique (TSA). Cependant, la plupart d'entre elles restent centrées sur l'individu et ne prennent pas en compte l'environnement social. Pour combler cette lacune, cette étude porte sur la conception centrée-utilisateur d'un outil en ligne, qui vise à soutenir la communication et la coordination entre les parents, le personnel scolaire et les professionnels médico-sociaux des élèves de collège et de lycée atteints de TSA, dans le contexte de l'élaboration, de la mise en œuvre et du suivi d'un projet personnalisé de scolarisation (PPS). L'étude a suivi un processus de conception en deux étapes : 1) une analyse des besoins pour identifier les domaines d'information jugés importants par les parties prenantes ; 2) par le biais d'un processus de conception participatif et itératif, un panel de professionnels et de parents a fourni des idées et des commentaires sur la conception, qui ont été intégrés dans les versions prototypes ultérieures de l'application "ToGather".

Dance requires skillful composition of complex movements that follow rhythmic, tonal and timbral features of music. Formally, generating dance conditioned on a piece of music can be expressed as a problem of modelling a high-dimensional continuous motion signal, conditioned on an audio signal. In this work we make two contributions to tackle this problem. First, we present a novel probabilistic autoregressive architecture that models the distribution over future poses with a normalizing flow conditioned on previous poses as well as music context, using a multimodal transformer encoder. Second, we introduce the currently largest 3D dance-motion dataset, obtained with a variety of motion-capture technologies, and including both professional and casual dancers. Using this dataset, we compare our new model against two baselines, via objective metrics and a user study, and show that both the ability to model a probability distribution, as well as being able to attend over a large motion and music context are necessary to produce interesting, diverse, and realistic dance that matches the music., Comment: Article presented at SIGGRAPH Asia 2021, and published in ACM Transactions on Graphics

International audience; Organizing information is beneficial to episodic memory performance. Among several possible organizational strategies, two consist of organizing the information in semantic clusters (semantic organization) or self-organizing the information based on new associations that do not exist in semantic memory (subjective organization). Here, we investigated in a single study how these two organizational behaviors were underlined by different controlled processes and whether these relations were subjected to age-related differences. We tested 123 younger adults (n = 63) and older adults (n = 60) on two episodic memory tasks, one where the words were organizable and another where the words were not organizable, allowing for semantic and subjective organization, respectively. Additionally, participants were tested on three cognitive control tasks (Wisconsin Card Sorting Test, Stroop Test and Trail Making Test) and three working memory tasks (Backward Digit Span, Alpha Span and N-back test). Results revealed well-established age-related differences in terms of recall performance and organizational strategy implementation. More importantly, we found evidence that the different cognitive tests statistically yielded two different latent factors, a cognitive control factor and a working memory factor. Based on this dissociation, we found that only cognitive control contributed to semantic organization in all age groups whereas only working memory contributed to subjective organization, also in all age groups. These results shed new lights on our understanding of how controlled processes differently contribute to organizational behaviors in episodic memory.

Recent works successfully leveraged Large Language Models' (LLM) abilities to capture abstract knowledge about world's physics to solve decision-making problems. Yet, the alignment between LLMs' knowledge and the environment can be wrong and limit functional competence due to lack of grounding. In this paper, we study an approach (named GLAM) to achieve this alignment through functional grounding: we consider an agent using an LLM as a policy that is progressively updated as the agent interacts with the environment, leveraging online Reinforcement Learning to improve its performance to solve goals. Using an interactive textual environment designed to study higher-level forms of functional grounding, and a set of spatial and navigation tasks, we study several scientific questions: 1) Can LLMs boost sample efficiency for online learning of various RL tasks? 2) How can it boost different forms of generalization? 3) What is the impact of online learning? We study these questions by functionally grounding several variants (size, architecture) of FLAN-T5.

Understanding the impact of robot errors in child-robot-interactions (CRI) is critical, as current technological systems are still limited and may randomly present a variety of mistakes during interactions with children. In this study we manipulate a task-based error of a NAO robot during a semi-autonomous computational thinking task implemented with the Cozmo robot. Data from 72 children aged 7–10 were analysed regarding their attitudes towards NAO (social trust, competency trust, liking, and perceived agency), their behaviour towards the robot (self-disclosure, following recommendations), as well as their task performance. We did not find quantitative effects of the robot’s error on children’s self-reported attitudes, behaviour, or task performance. Age was also not significantly related to either social attitudes or behaviours towards NAO, although there were some age-related differences in task performance. Potential reasons behind the lack of statistical effects and limitations of the study with regards to the manipulation of robot errors are discussed and insights into the design of future CRI studies provided.

Lenia is a family of cellular automata (CA) generalizing Conway's Game of Life to continuous space, time and states. Lenia has attracted a lot of attention because of the wide diversity of self-organizing patterns it can generate. Among those, some spatially localized patterns (SLPs) resemble life-like artificial creatures. However, those creatures are found in only a small subspace of the Lenia parameter space and are not trivial to discover, necessitating advanced search algorithms. We hypothesize that adding a mass conservation constraint could facilitate the emergence of SLPs. We propose here an extension of the Lenia model, called Flow Lenia, which enables mass conservation. We show a few observations demonstrating its effectiveness in generating SLPs with complex behaviors. Furthermore, we show how Flow Lenia enables the integration of the parameters of the CA update rules within the CA dynamics, making them dynamic and localized. This allows for multi-species simulations, with locally coherent update rules that define properties of the emerging creatures, and that can be mixed with neighbouring rules. We argue that this paves the way for the intrinsic evolution of self-organized artificial life forms within continuous CAs.

In order to train children's ability to ask curiosity-driven questions, previous research has explored designing specific exercises relying on providing semantic and linguistic cues to help formulate such questions. But despite showing pedagogical efficiency, this method is still limited as it relies on generating the said cues by hand, which can be a very costly process. In this context, we propose to leverage advances in the natural language processing field (NLP) and investigate the efficiency of using a large language model (LLM) for automating the production of the pedagogical content of a curious question-asking (QA) training. We study generating the said content using the "prompt-based" method that consists of explaining the task to the LLM in natural text. We evaluate the output using human experts annotations and comparisons with hand-generated content. Results suggested indeed the relevance and usefulness of this content. We also conduct a field study in primary school (75 children aged 9-10), where we evaluate children's QA performance when having this training. We compare 3 types of content : 1) hand-generated content that proposes "closed" cues leading to predefined questions; 2) GPT-3-generated content that proposes the same type of cues; 3) GPT-3-generated content that proposes "open" cues leading to several possible questions. We see a similar QA performance between the two "closed" trainings (showing the scalability of the approach using GPT-3), and a better one for participants with the "open" training. These results suggest the efficiency of using LLMs to support children in generating more curious questions, using a natural language prompting approach that affords usability by teachers and other users not specialists of AI techniques. Furthermore, results also show that open-ended content may be more suitable for training curious question-asking skills.

The framework of Language Games studies the emergence of languages in populations of agents. Recent contributions relying on deep learning methods focused on agents communicating via an idealized communication channel, where utterances produced by a speaker are directly perceived by a listener. This comes in contrast with human communication, which instead relies on a sensory-motor channel, where motor commands produced by the speaker (e.g. vocal or gestural articulators) result in sensory effects perceived by the listener (e.g. audio or visual). Here, we investigate if agents can evolve a shared language when they are equipped with a continuous sensory-motor system to produce and perceive signs, e.g. drawings. To this end, we introduce the Graphical Referential Game (GREG) where a speaker must produce a graphical utterance to name a visual referent object consisting of combinations of MNIST digits while a listener has to select the corresponding object among distractor referents, given the produced message. The utterances are drawing images produced using dynamical motor primitives combined with a sketching library. To tackle GREG we present CURVES: a multimodal contrastive deep learning mechanism that represents the energy (alignment) between named referents and utterances generated through gradient ascent on the learned energy landscape. We, then, present a set of experiments and metrics based on a systematic compositional dataset to evaluate the resulting language. We show that our method allows the emergence of a shared, graphical language with compositional properties.

How can a population of reinforcement learning agents autonomously learn a diversity of cooperative tasks in a shared environment? In the single-agent paradigm, goal-conditioned policies have been combined with intrinsic motivation mechanisms to endow agents with the ability to master a wide diversity of autonomously discovered goals. Transferring this idea to cooperative multi-agent systems (MAS) entails a challenge: intrinsically motivated agents that sample goals independently focus on a shared cooperative goal with low probability, impairing their learning performance. In this work, we propose a new learning paradigm for modeling such settings, the Decentralized Intrinsically Motivated Skill Acquisition Problem (Dec-IMSAP), and employ it to solve cooperative navigation tasks. Agents in a Dec-IMSAP are trained in a fully decentralized way, which comes in contrast to previous contributions in multi-goal MAS that consider a centralized goal-selection mechanism. Our empirical analysis indicates that a sufficient condition for efficiently learning a diversity of cooperative tasks is to ensure that a group aligns its goals, i.e., the agents pursue the same cooperative goal and learn to coordinate their actions through specialization. We introduce the Goal-coordination game, a fully-decentralized emergent communication algorithm, where goal alignment emerges from the maximization of individual rewards in multi-goal cooperative environments and show that it is able to reach equal performance to a centralized training baseline that guarantees aligned goals. To our knowledge, this is the first contribution addressing the problem of intrinsically motivated multi-agent goal exploration in a decentralized training paradigm.

Large Language Models (LLMs) have in recent years demonstrated impressive prowess in natural language generation. A common practice to improve generation diversity is to sample multiple outputs from the model. However, there lacks a simple and robust way of selecting the best output from these stochastic samples. As a case study framed in the context of question generation, we propose two prompt-based approaches to selecting high-quality questions from a set of LLM-generated candidates. Our method works under the constraints of 1) a black-box (non-modifiable) question generation model and 2) lack of access to human-annotated references -- both of which are realistic limitations for real-world deployment of LLMs. With automatic as well as human evaluations, we empirically demonstrate that our approach can effectively select questions of higher qualities than greedy generation.

International audience; End-to-end reinforcement learning on images showed significant performance progress in the recent years, especially with regularization to value estimation brought by data augmentation (Yarats et al., 2020). At the same time, domain randomization and representation learning helped push the limits of these algorithms in visually diverse environments, full of distractors and spurious noise, making RL more robust to unrelated visual features. We present DIQL, a method that combines risk invariant regularization and domain randomization to reduce out-of-distribution (OOD) generalization gap for temporal-difference learning. In this work, we draw a link by framing domain randomization as a richer extension of data augmentation to RL and support its generalized use. Our model-free approach improve baselines performances without the need of additional representation learning objectives and with limited additional computational cost. We show that DIQL outperforms existing methods on complex visuo-motor control environment with high visual perturbation. In particular, our approach achieves state-of the-art performance on the Distracting Control Suite benchmark, where we evaluate the robustness to a number of visual perturbators, as well as OOD generalization and extrapolation capabilities.

An intriguing feature of the human species is our ability to continuously invent new problems and to proactively acquiring new skills in order to solve them: what is called open-ended skill acquisition (OESA). Understanding the mechanisms underlying OESA is an important scientific challenge in both cognitive science (e.g. by studying infant cognitive development) and in artificial intelligence (aiming at computational architectures capable of open-ended learning). Both fields, however, mostly focus on cognitive and social mechanisms at the scale of an individual’s life. It is rarely acknowledged that OESA, an ability that is fundamentally related to the characteristics of human intelligence, has been necessarily shaped by ecological, evolutionary and cultural mechanisms interacting at multiple spatiotemporal scales. In this thesis, I present a research program aiming at understanding, modelingand simulating the dynamics of OESA in artificial systems, grounded in theories studying its eco-evolutionary bases in the human species. It relies on a conceptual framework expressing the complex interactions between environmental, adaptive, multi-agent and cultural dynamics. Three main research questions are developed and I present a selection of my contributions for each of them.- What are the ecological conditions favoring the evolution of skill acquisition?- How to bootstrap the formation of a cultural repertoire in populations of adaptive agents?- What is the role of cultural evolution in the open-ended dynamics of human skill acquisition?By developing these topics, we will reveal interesting relationships between theories in human evolution and recent approaches in artificial intelligence. This will lead to the proposition of a humanist perspective on AI: using it as a family of computational tools that can help us to explore and study the mechanisms driving open-ended skill acquisition in both artificial and biological systems, as a way to better understand the dynamics of our own species within its whole ecological context. This document presents an overview of my scientific trajectory since the start of my PhD thesis in 2007, the detail of my current research program, a selection of my contributions as well as perspectives for future work.

International audience

International audience

International audience; Curiosity is an important factor that enables independent learning in children. Research suggests that it is also a competence that can be fostered by training specific metacognitive skills and information-searching behaviors. In this light, we develop a conversational agent that helps children generate curiosity-driven questions, and encourages their use to lead autonomous explorations and gain new knowledge. The study was conducted with 51 primary school students aged between 9 and 10 years old who interacted with either a neutral agent or an “incentive” agent that helped curiosity-driven questioning by offering specific semantic cues. Results showed a significant increase in the number and the quality of the questions generated with the “incentive” agent. This interaction also resulted in longer explorations and stronger learning progress.Together, our results suggest that the more our agent is able to train children’s curiosity-related metacognitive skills, the better they can maintain their information-searching behaviors and the more new knowledge they are likely to acquire.

International audience; In this article, we present an original neural space/latency code, integrated in a multi-layered neural hierarchy, that offers a new perspective on probabilistic inference operations. Our work is based on the dynamic neural field paradigm that leads to the emergence of activity bumps, based on recurrent lateral interactions, thus providing a spatial coding of information. We propose that lateral connections represent a data model, i.e., the conditional probability of a "true" stimulus given a noisy input. We propose furthermore that the resulting attractor state encodes the most likely "true" stimulus given the data model, and that its latency expresses the confidence in this interpretation. Thus, the main feature of this network is its ability to represent, transmit and integrate probabilistic information at multiple levels so that to take near-optimal decisions when inputs are contradictory, noisy or missing. We illustrate these properties on a three-layered neural hierarchy receiving inputs from a simplified robotic object recognition task. We also compare the network dynamics to an explicit probabilistic model of the task, to verify that it indeed reproduces all relevant properties of probabilistic processing.

National audience

To solve difficult tasks, humans ask questions to acquire knowledge from external sources. In contrast, classical reinforcement learning agents lack such an ability and often resort to exploratory behavior. This is exacerbated as few present-day environments support querying for knowledge. In order to study how agents can be taught to query external knowledge via language, we first introduce two new environments: the grid-world-based Q-BabyAI and the text-based Q-TextWorld. In addition to physical interactions, an agent can query an external knowledge source specialized for these environments to gather information. Second, we propose the "Asking for Knowledge" (AFK) agent, which learns to generate language commands to query for meaningful knowledge that helps solve the tasks. AFK leverages a non-parametric memory, a pointer mechanism and an episodic exploration bonus to tackle (1) irrelevant information, (2) a large query language space, (3) delayed reward for making meaningful queries. Extensive experiments demonstrate that the AFK agent outperforms recent baselines on the challenging Q-BabyAI and Q-TextWorld environments., Comment: ICML 2022; Project page: https://ioujenliu.github.io/AFK/

Building autonomous machines that can explore open-ended environments, discover possible interactions and build repertoires of skills is a general objective of artificial intelligence. Developmental approaches argue that this can only be achieved by $autotelic$ $agents$: intrinsically motivated learning agents that can learn to represent, generate, select and solve their own problems. In recent years, the convergence of developmental approaches with deep reinforcement learning (RL) methods has been leading to the emergence of a new field: $developmental$ $reinforcement$ $learning$. Developmental RL is concerned with the use of deep RL algorithms to tackle a developmental problem -- the $intrinsically$ $motivated$ $acquisition$ $of$ $open$-$ended$ $repertoires$ $of$ $skills$. The self-generation of goals requires the learning of compact goal encodings as well as their associated goal-achievement functions. This raises new challenges compared to standard RL algorithms originally designed to tackle pre-defined sets of goals using external reward signals. The present paper introduces developmental RL and proposes a computational framework based on goal-conditioned RL to tackle the intrinsically motivated skills acquisition problem. It proceeds to present a typology of the various goal representations used in the literature, before reviewing existing methods to learn to represent and prioritize goals in autonomous systems. We finally close the paper by discussing some open challenges in the quest of intrinsically motivated skills acquisition.

Reinforcement learning (RL) in long horizon and sparse reward tasks is notoriously difficult and requires a lot of training steps. A standard solution to speed up the process is to leverage additional reward signals, shaping it to better guide the learning process. In the context of language-conditioned RL, the abstraction and generalisation properties of the language input provide opportunities for more efficient ways of shaping the reward. In this paper, we leverage this idea and propose an automated reward shaping method where the agent extracts auxiliary objectives from the general language goal. These auxiliary objectives use a question generation (QG) and question answering (QA) system: they consist of questions leading the agent to try to reconstruct partial information about the global goal using its own trajectory. When it succeeds, it receives an intrinsic reward proportional to its confidence in its answer. This incentivizes the agent to generate trajectories which unambiguously explain various aspects of the general language goal. Our experimental study shows that this approach, which does not require engineer intervention to design the auxiliary objectives, improves sample efficiency by effectively directing exploration., 24 pages, 16 figures, 5 tables

International audience; COSMO ("Communicating Objects by Sensory-Motor Operations") is a framework for jointly modeling speech perception and production by considering sensory-motor relations as a core component of its program. COSMO allows to jointly formalize two major theoretical frameworks in speech research that are auditory and motor theories – but also to integrate them within perceptual-motor theories. This leads to new perception models associating auditory processing and motor knowledge, and new speech motor control models oriented toward the achievement of multimodal sensory goals. We present the main results obtained with COSMO, and perspectives about temporal processing and deep learning implementation allowing to get closer to learning on real data.; Nous avons développé un cadre de modélisation des processus de la communication parlée, COSMO (« Communicating Objects by Sensory-Motor Operations »), qui s'applique à la fois aux modèles de perception et de production de parole en installant les relations sensori-motrices au coeur de son programme. COSMO permet de formaliser conjointement deux cadres théoriques majeurs des recherches sur la communication parlée, les théories auditives et motrices-mais aussi de les intégrer au sein de théories perceptuo-motrices. Ceci conduit ainsi à de nouveaux modèles de perception alliant traitements auditifs et prise en compte de connaissances motrices, ou de nouveaux modèles de contrôle moteur de la parole orientés vers la réalisation de buts sensoriels multimodaux. Nous présentons ces avancées ainsi que des pistes de développement sur le traitement temporel et l'implémentation deep learning permettant d'aller vers l'apprentissage sur des données réelles.

International audience; Cognitive test batteries are widely used in diverse research fields, such as cognitive training, cognitive disorder assessment, or brain mechanism understanding. Although they need flexibility according to their usage objectives, most test batteries are not available as open-source software and are not be tuned by researchers in detail. The present study introduces an open-source cognitive test battery to assess attention and memory, using a javascript library, p5.js. Because of the ubiquitous nature of dynamic attention in our daily lives, it is crucial to have tools for its assessment or training. For that purpose, our test battery includes seven cognitive tasks (multiple-objects tracking, enumeration, go/no-go, load-induced blindness, task-switching, working memory, and memorability), common in cognitive science literature. By using the test battery, we conducted an online experiment to collect the benchmark data. Results conducted on 2 separate days showed the high cross-day reliability. Specifically, the task performance did not largely change with the different days. Besides, our test battery captures diverse individual differences and can evaluate them based on the cognitive factors extracted from latent factor analysis. Since we share our source code as open-source software, users can expand and manipulate experimental conditions flexibly. Our test battery is also flexible in terms of the experimental environment, i.e., it is possible to experiment either online or in a laboratory environment.

The human cultural repertoire relies on innovation: our ability to continuously and hierarchically explore how existing elements can be combined to create new ones. Innovation is not solitary, it relies on collective accumulation and merging of previous solutions. Machine learning approaches commonly assume that fully connected multi-agent networks are best suited for innovation. However, human laboratory and field studies have shown that hierarchical innovation is more robustly achieved by dynamic communication topologies. In dynamic topologies, humans oscillate between innovating individually or in small clusters, and then sharing outcomes with others. To our knowledge, the role of multi-agent topology on innovation has not been systematically studied in machine learning. It remains unclear a) which communication topologies are optimal for which innovation tasks, and b) which properties of experience sharing improve multi-level innovation. Here we use a multi-level hierarchical problem setting (WordCraft), with three different innovation tasks. We systematically design networks of DQNs sharing experiences from their replay buffers in varying topologies (fully connected, small world, dynamic, ring). Comparing the level of innovation achieved by different experience-sharing topologies across different tasks shows that, first, consistent with human findings, experience sharing within a dynamic topology achieves the highest level of innovation across tasks. Second, experience sharing is not as helpful when there is a single clear path to innovation. Third, two metrics we propose, conformity and diversity of shared experience, can explain the success of different topologies on different tasks. These contributions can advance our understanding of optimal AI-AI, human-human, and human-AI collaborative networks, inspiring future tools for fostering collective innovation in large organizations.

International audience; Semantic Dysmnesia is a disorder that is not often mentioned in the literature and is not well identified in child and adolescent clinics, although some studies on this disorder put forward a prevalence of about 6%. We present the case of Léthé which illustrates both the clinical picture and two hypotheses put forward in the literature to explain the lack of recognition. This clinical case was focused on the realization of a psychological assessment following the first alert in order to propose guidelines to identify the cognitive disorder with the WISC-V as a first intention and complementary batteries on the transversal cognitive functions. This case study completes the literature on the clinical elements to be identified and on the etiology of dysmnesia.; La dysmnésie en mémoire à long terme sémantique est un trouble peu évoqué dans la littérature et peu identifié en clinique de l’enfant et de l’adolescent, bien que quelques travaux sur ce trouble mettent en avant une prévalence d’environ 6 %. Nous présentons le cas de Léthé qui illustre tant le tableau clinique que deux hypothèses avancées dans la littérature pour expliquer le manque de reconnaissance de ce trouble. Ce cas clinique a e´ te´ centre´ sur la réalisation d’un bilan psychologique suite aux premiers signes d’alerte afin de proposer des guidelines pour identifier ce trouble cognitif, avec en première intention la WISC-V et des batteries complémentaires sur les fonctions cognitives transversales. Cette étude de cas permet de compléter la littérature sur les éléments cliniques a` identifier et sur l’étiologie de la dysmnésie.

International audience

International audience

International audience; D’après le modèle CIF-EA (OMS, 2007), les interventions à destination des enfants et adolescents avec trouble du spectre autistique (TSA) doivent répondre à un double-enjeu : réduire le retentissement du TSA sur la vie de l’individu pour diminuer les limitations d’activités et soutenir la personne dans ses activités quotidiennes et scolaires pour lever les barrières à sa participation sociale, notamment dans les milieux scolaires ordinaires. Dans ce contexte, les technologies de l’information et de la communication (TIC) sont plébiscitées pour proposer de nouvelles voies d’accompagnement des enfants et adolescents avec TSA pour les soutenir au quotidien et promouvoir leur scolarisation en milieu ordinaire. Aujourd’hui, les TIC font l’objet d’un nombre croissant de recherches, qui, au fil des années, ont fait levier sur une variété de technologies (robots, ordinateurs, tablettes, etc.). Néanmoins, il reste des défis à relever pour proposer des outils toujours plus adaptés aux besoins et envies des enfants et adolescents avec TSA et à ceux de leurs aidants (famille, école, professionnels médico-sociaux et de l’accompagnement), et mieux contribuer à l’épanouissement et à la réalisation des projets de vie des individus avec TSA. Après une brève synthèse des recherches sur les TIC pour les enfants et adolescents avec TSA, cette communication sera consacrée à l’exploration de ces défis au travers de thèmes tels que l’évolution des contenus d’intervention, des méthodes de conception et d’évaluation, et sera l’occasion d’évoquer les perspectives de recherche pour les relever.

International audience; Despite its rise as a prominent solution to the data inefficiency of today's machine learning models, self-supervised learning has yet to be studied from a purely multi-agent perspective. In this work, we propose that aligning internal subjective representations, which naturally arise in a multi-agent setup where agents receive partial observations of the same underlying environmental state, can lead to more data-efficient representations. We propose that multi-agent environments, where agents do not have access to the observations of others but can communicate within a limited range, guarantees a common context that can be leveraged in individual representation learning. The reason is that subjective observations necessarily refer to the same subset of the underlying environmental states and that communication about these states can freely offer a supervised signal. To highlight the importance of communication, we refer to our setting as \textit{socially supervised representation learning}. We present a minimal architecture comprised of a population of autoencoders, where we define loss functions, capturing different aspects of effective communication, and examine their effect on the learned representations. We show that our proposed architecture allows the emergence of aligned representations. The subjectivity introduced by presenting agents with distinct perspectives of the environment state contributes to learning abstract representations that outperform those learned by a single autoencoder and a population of autoencoders, presented with identical perspectives of the environment state. Altogether, our results demonstrate how communication from subjective perspectives can lead to the acquisition of more abstract representations in multi-agent systems, opening promising perspectives for future research at the intersection of representation learning and emergent communication.

Objective We investigated how participants controlling a humanoid robotic arm’s 3D endpoint position by moving their own hand are influenced by the robot’s postures. We hypothesized that control would be facilitated (impeded) by biologically plausible (implausible) postures of the robot. Background Kinematic redundancy, whereby different arm postures achieve the same goal, is such that a robotic arm or prosthesis could theoretically be controlled with less signals than constitutive joints. However, congruency between a robot’s motion and our own is known to interfere with movement production. Hence, we expect the human-likeness of a robotic arm’s postures during endpoint teleoperation to influence controllability. Method Twenty-two able-bodied participants performed a target-reaching task with a robotic arm whose endpoint’s 3D position was controlled by moving their own hand. They completed a two-condition experiment corresponding to the robot displaying either biologically plausible or implausible postures. Results Upon initial practice in the experiment’s first part, endpoint trajectories were faster and shorter when the robot displayed human-like postures. However, these effects did not persist in the second part, where performance with implausible postures appeared to have benefited from initial practice with plausible ones. Conclusion Humanoid robotic arm endpoint control is impaired by biologically implausible joint coordinations during initial familiarization but not afterwards, suggesting that the human-likeness of a robot’s postures is more critical for control in this initial period. Application These findings provide insight for the design of robotic arm teleoperation and prosthesis control schemes, in order to favor better familiarization and control from their users.

International audience; Hierarchical Reinforcement Learning (HRL) offers potential benefits for solving long horizon tasks, generally unhandled by standard Reinforcement Learning (RL) techniques, by decomposing the problem and combining simple policies to achieve the goal. They are however still held back by the curse of dimensionality and the ambiguity of selected subtasks. We explore relevant approaches in HRL while highlighting the key challenges of goal representation, high-level planning and propose a research outline tackling them.

We are interested in interactive agents that learn to coordinate, namely, a $builder$ -- which performs actions but ignores the goal of the task, i.e. has no access to rewards -- and an $architect$ which guides the builder towards the goal of the task. We define and explore a formal setting where artificial agents are equipped with mechanisms that allow them to simultaneously learn a task while at the same time evolving a shared communication protocol. Ideally, such learning should only rely on high-level communication priors and be able to handle a large variety of tasks and meanings while deriving communication protocols that can be reused across tasks. We present the Architect-Builder Problem (ABP): an asymmetrical setting in which an architect must learn to guide a builder towards constructing a specific structure. The architect knows the target structure but cannot act in the environment and can only send arbitrary messages to the builder. The builder on the other hand can act in the environment, but receives no rewards nor has any knowledge about the task, and must learn to solve it relying only on the messages sent by the architect. Crucially, the meaning of messages is initially not defined nor shared between the agents but must be negotiated throughout learning. Under these constraints, we propose Architect-Builder Iterated Guiding (ABIG), a solution to ABP where the architect leverages a learned model of the builder to guide it while the builder uses self-imitation learning to reinforce its guided behavior. We analyze the key learning mechanisms of ABIG and test it in 2D tasks involving grasping cubes, placing them at a given location, or building various shapes. ABIG results in a low-level, high-frequency, guiding communication protocol that not only enables an architect-builder pair to solve the task at hand, but that can also generalize to unseen tasks., Comment: International Conference on Learning Representations (2022)

International audience; Les Technologies d’Assistance numériques (TAn), visant à soutenir l’autonomie et la participation sociale des personnes âgées, sont un domaine en pleine expansion, comme en témoignent l’offre commerciale et les recherches actuelles. En effet, les avancées technologiques observées permettent d’envisager cette voie comme prometteuse et porteuse de progrès médico-social pour les personnes concernées. Pour dépasser les limites de l’approche techno-centrée, générant des produits souvent inadaptés aux besoins des futurs utilisateurs âgés et clamant des allégations de santé non justifiées scientifiquement, une approche intégrée est présentée alliant les modèles ergonomiques de conception centrée-utilisateur et les méthodes expérimentales de validation clinique, avec une emphase donnée aux mécanismes de motivation intrinsèque liés à l’auto-détermination. Pour illustration, est exposée une série de travaux portant sur une plateforme d’objets connectés pour l’assistance domiciliaire de personnes âgées fragiles, appelée DomAssist. Ces travaux ont été menés depuis la conception jusqu’au déploiement de la plateforme sur le terrain, avec des validations scientifiques amont (ergonomie et motivation suscitée) et aval (étude pilote des gains cliniques auprès des personnes âgées fragiles et/ou leurs aidants). Au final, des résultats prometteurs sont obtenus : la solution DomAssist chez la personne âgée fragile génère une bonne expérience utilisateur, améliore le sentiment d’auto-détermination, retarde les dégradations fonctionnelles, et enfin réduit le fardeau des aidants dans l’aide qu’ils apportent pour le fonctionnement quotidien de la personne âgée.

A long-standing goal of Machine Learning (ML) and AI at large is to design autonomous agents able to efficiently interact with our world. Towards this, taking inspirations from the interactive nature of human and animal learning, several lines of works focused on building decision making agents embodied in real or virtual environments. In less than a decade, Deep Reinforcement Learning (DRL) established itself as one of the most powerful set of techniques to train such autonomous agents. DRL is based on the maximization of expert-defined reward functions that guide an agent’s learning towards a predefined target task or task set. In parallel, the Developmental Robotics field has been working on modelling cognitive development theories and integrating them into real or simulated robots. A core concept developed in this literature is the notion of intrinsic motivation: developmental robots explore and interact with their environment according to self-selected objectives in an open-ended learning fashion. Recently, similar ideas of self-motivation and open-ended learning started to grow within the DRL community, while the Developmental Robotics community started to consider DRL methods into their developmental systems. We propose to refer to this convergence of works as Developmental Machine Learning. Developmental ML regroups works on building embodied autonomous agents equipped with intrinsic-motivation mechanisms shaping open-ended learning trajectories. The present research aims to contribute within this emerging field. More specifically, the present research focuses on proposing and assessing the performance of a core algorithmic block of such developmental machine learners: Automatic Curriculum Learning (ACL) methods. ACL algorithms shape the learning trajectories of agents by challenging them with tasks adapted to their capacities. In recent years, they have been used to improve sample efficiency and asymptotic performance, to organize exploration, to encourage generalization or to solve sparse reward problems, among others. Despite impressive success in traditional supervised learning scenarios (e.g. image classification), large-scale and real-world applications of embodied machine learners are yet to come. The present research aims to contribute towards the creation of such agents by studying how to autonomously and efficiently scaffold them up to proficiency.; Un objectif de longue date du Machine Learning (ML) et de l'IA en général est de concevoir des agents autonomes capables d'interagir efficacement avec notre monde. Dans cette optique, s'inspirant de la nature interactive de l'apprentissage humain et animal, plusieurs axes de travaux se sont concentrés sur la construction d'agents décisionnels incarnés dans des environnements réels ou virtuels. En moins d'une décennie, le Deep Reinforcement Learning (DRL) s'est imposé comme l'un des ensembles de techniques les plus puissants pour former de tels agents autonomes. Le DRL est basé sur la maximisation de fonctions de récompense définies par des experts qui guident l'apprentissage d'un agent vers une tâche ou un ensemble de tâches cible prédéfinies. En parallèle, la Robotique Développementale a travaillé sur la modélisation des théories du développement cognitif et de leur intégration dans des robots réels ou simulés. Un concept central développé dans cette littérature est la notion de motivation intrinsèque : les robots développementaux explorent et interagissent avec leur environnement selon des objectifs auto-sélectionnés dans un mode d'apprentissage ouvert. Récemment, des idées similaires d'auto-motivation et d'apprentissage ouvert ont commencé à se développer au sein de la communauté DRL, tandis que la Robotique Développementale a commencé à considérer les méthodes DRL dans leurs systèmes de développement. Nous proposons de désigner cette convergence de travaux sous le nom de Developmental Machine Learning. Developmental ML regroupe des travaux sur la construction d'agents autonomes incarnés équipés de mécanismes de motivation intrinsèque façonnant des trajectoires d'apprentissage ouvertes. La présente recherche vise à contribuer dans ce domaine émergent. Plus précisément, la présente recherche se concentre sur la proposition et l'évaluation des performances d'un bloc algorithmique de base de tels apprenants: les méthodes d'apprentissage automatique de curriculum (ACL). Les algorithmes ACL façonnent les trajectoires d'apprentissage des agents en les challengeant avec des tâches adaptées à leurs compétences. Ces dernières années, ils ont été utilisés pour améliorer la vitesse d’apprentissage et les performances asymptotiques, pour organiser l'exploration, pour encourager la généralisation ou pour résoudre des problèmes de récompense clairsemée, entre autres. Malgré un succès impressionnant dans les scénarios d'apprentissage supervisé traditionnels (par exemple, la classification d'images), les applications à grande échelle et dans le monde réel des apprenants automatiques incarnés sont encore à venir. La présente recherche vise à contribuer à la création de tels agents en étudiant comment guider leurs apprentissage de manière autonome.