Mohamed Chetouani

Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani

Learning from demonstration methods usually leverage close to optimal demonstrations to accelerate training. By contrast, when demonstrating a task, human teachers deviate from optimal demonstrations and pedagogically modify their behavior by giving demonstrations that best disambiguate the goal they want to demonstrate. Analogously, human learners excel at pragmatically inferring the intent of the teacher, facilitating communication between the two agents. These mechanisms are critical in the few demonstrations regime, where inferring the goal is more difficult. In this paper, we implement pedagogy and pragmatism mechanisms by leveraging a Bayesian model of Goal Inference from demonstrations (BGI). We highlight the benefits of this model in multi-goal teacher-learner setups with two artificial agents that learn with goal-conditioned Reinforcement Learning. We show that combining BGI-agents (a pedagogical teacher and a pragmatic learner) results in faster learning and reduced goal ambiguity over standard learning from demonstrations, especially in the few demonstrations regime. We provide the code for our experiments (https://github.com/Caselles/NeurIPS22-demonstrations-pedagogy-pragmatism), as well as an illustrative video explaining our approach (https://youtu.be/V4n16IjkNyw).

Sera Buyukgoz, Jasmin Grosinger, Mohamed Chetouani et al.

Robots sharing their space with humans need to be proactive in order to be helpful. Proactive robots are able to act on their own initiative in an anticipatory way to benefit humans. In this work, we investigate two ways to make robots proactive. One way is to recognize humans' intentions and to act to fulfill them, like opening the door that you are about to cross. The other way is to reason about possible future threats or opportunities and to act to prevent or to foster them, like recommending you to take an umbrella since rain has been forecasted. In this paper, we present approaches to realize these two types of proactive behavior. We then present an integrated system that can generate proactive robot behavior by reasoning on both factors: intentions and predictions. We illustrate our system on a sample use case including a domestic robot and a human. We first run this use case with the two separate proactive systems, intention-based and prediction-based, and then run it with our integrated system. The results show that the integrated system is able to take into account a broader variety of aspects that are needed for proactivity.

Hanan Salam, Oya Celiktutan, Hatice Gunes et al.

An integral part of seamless human-human communication is engagement, the process by which two or more participants establish, maintain, and end their perceived connection. Therefore, to develop successful human-centered human-machine interaction applications, automatic engagement inference is one of the tasks required to achieve engaging interactions between humans and machines, and to make machines attuned to their users, hence enhancing user satisfaction and technology acceptance. Several factors contribute to engagement state inference, which include the interaction context and interactants' behaviours and identity. Indeed, engagement is a multi-faceted and multi-modal construct that requires high accuracy in the analysis and interpretation of contextual, verbal and non-verbal cues. Thus, the development of an automated and intelligent system that accomplishes this task has been proven to be challenging so far. This paper presents a comprehensive survey on previous work in engagement inference for human-machine interaction, entailing interdisciplinary definition, engagement components and factors, publicly available datasets, ground truth assessment, and most commonly used features and methods, serving as a guide for the development of future human-machine interaction interfaces with reliable context-aware engagement inference capability. An in-depth review across embodied and disembodied interaction modes, and an emphasis on the interaction context of which engagement perception modules are integrated sets apart the presented survey from existing surveys.

Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani

Teaching an agent to perform new tasks using natural language can easily be hindered by ambiguities in interpretation. When a teacher provides an instruction to a learner about an object by referring to its features, the learner can misunderstand the teacher's intentions, for instance if the instruction ambiguously refer to features of the object, a phenomenon called referential ambiguity. We study how two concepts derived from cognitive sciences can help resolve those referential ambiguities: pedagogy (selecting the right instructions) and pragmatism (learning the preferences of the other agents using inductive reasoning). We apply those ideas to a teacher/learner setup with two artificial agents on a simulated robotic task (block-stacking). We show that these concepts improve sample efficiency for training the learner.

Clémence Grislain, Hugo Caselles-Dupré, Olivier Sigaud et al.

Good teachers always tailor their explanations to the learners. Cognitive scientists model this process under the rationality principle: teachers try to maximise the learner's utility while minimising teaching costs. To this end, human teachers seem to build mental models of the learner's internal state, a capacity known as Theory of Mind (ToM). Inspired by cognitive science, we build on Bayesian ToM mechanisms to design teacher agents that, like humans, tailor their teaching strategies to the learners. Our ToM-equipped teachers construct models of learners' internal states from observations and leverage them to select demonstrations that maximise the learners' rewards while minimising teaching costs. Our experiments in simulated environments demonstrate that learners taught this way are more efficient than those taught in a learner-agnostic way. This effect gets stronger when the teacher's model of the learner better aligns with the actual learner's state, either using a more accurate prior or after accumulating observations of the learner's behaviour. This work is a first step towards social machines that teach us and each other, see https://teacher-with-tom.github.io.

Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani

We introduce a novel category of GC-agents capable of functioning as both teachers and learners. Leveraging action-based demonstrations and language-based instructions, these agents enhance communication efficiency. We investigate the incorporation of pedagogy and pragmatism, essential elements in human communication and goal achievement, enhancing the agents' teaching and learning capabilities. Furthermore, we explore the impact of combining communication modes (action and language) on learning outcomes, highlighting the benefits of a multi-modal approach.

Asma Amalas, Mounir Ghogho, Mohamed Chetouani et al.

Recent speech technologies have led to produce high quality synthesised speech due to recent advances in neural Text to Speech (TTS). However, such TTS models depend on extensive amounts of data that can be costly to produce and is hardly scalable to all existing languages, especially that seldom attention is given to low resource languages. With techniques such as knowledge transfer, the burden of creating datasets can be alleviated. In this paper, we therefore investigate two aspects; firstly, whether data from social media can be used for a small TTS dataset construction, and secondly whether cross lingual transfer learning (TL) for a low resource language can work with this type of data. In this aspect, we specifically assess to what extent multilingual modeling can be leveraged as an alternative to training on monolingual corporas. To do so, we explore how data from foreign languages may be selected and pooled to train a TTS model for a target low resource language. Our findings show that multilingual pre-training is better than monolingual pre-training at increasing the intelligibility and naturalness of the generated speech.

Mohamed Salim Aissi, Clemence Grislain, Clement Romac et al.

Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap in standalone Vision-Language Models (VLMs), which often overlook task-critical information. In this paper, we introduce PRISM, a framework that tightly couples perception (VLM) and decision (LLM) through a dynamic question-answer (DQA) pipeline. Instead of passively accepting the VLM's description, the LLM critiques it, probes the VLM with goal-oriented questions, and synthesizes a compact image description. This closed-loop interaction yields a sharp, task-driven understanding of the scene. We evaluate PRISM on the ALFWorld and Room-to-Room (R2R) benchmarks. We show that: (1) PRISM significantly outperforms state-of-the-art image-based models, (2) our Interactive goal-oriented perception pipeline yields systematic and substantial gains, and (3) PRISM is fully automatic, eliminating the need for handcrafted questions or answers.

Hamed Rahimi, Adil Bahaj, Mouad Abrini et al.

The integration of vision-language models into robotic systems constitutes a significant advancement in enabling machines to interact with their surroundings in a more intuitive manner. While VLMs offer rich multimodal reasoning, existing approaches lack user-specific adaptability, often relying on generic interaction paradigms that fail to account for individual behavioral, contextual, or socio-emotional nuances. When customization is attempted, ethical concerns arise from unmitigated biases in user data, risking exclusion or unfair treatment. To address these dual challenges, we propose User-VLM 360°, a holistic framework integrating multimodal user modeling with bias-aware optimization. Our approach features: (1) user-aware tuning that adapts interactions in real time using visual-linguistic signals; (2) bias mitigation via preference optimization; and (3) curated 360° socio-emotive interaction datasets annotated with demographic, emotion, and relational metadata. Evaluations across eight benchmarks demonstrate state-of-the-art results: +35.3% F1 in personalized VQA, +47.5% F1 in facial features understanding, 15% bias reduction, and 30X speedup over baselines. Ablation studies confirm component efficacy, and deployment on the Pepper robot validates real-time adaptability across diverse users. We open-source parameter-efficient 3B/10B models and an ethical verification framework for responsible adaptation.

Adrien Jacquet Crétides, Mouad Abrini, Hamed Rahimi et al.

Striking a balance between efficiency and transparent motion is a core challenge in human-robot collaboration, as highly expressive movements often incur unnecessary time and energy costs. In collaborative environments, legibility allows a human observer a better understanding of the robot's actions, increasing safety and trust. However, these behaviors result in sub-optimal and exaggerated trajectories that are redundant in low-ambiguity scenarios where the robot's goal is already obvious. To address this trade-off, we propose Style-Conditioned Diffusion Policy (SCDP), a modular framework that constrains the trajectory generation of a pre-trained diffusion model toward either legibility or efficiency based on the environment's configuration. Our method utilizes a post-training pipeline that freezes the base policy and trains a lightweight scene encoder and conditioning predictor to modulate the diffusion process. At inference time, an ambiguity detection module activates the appropriate conditioning, prioritizing expressive motion only for ambiguous goals and reverting to efficient paths otherwise. We evaluate SCDP on manipulation and navigation tasks, and results show that it enhances legibility in ambiguous settings while preserving optimal efficiency when legibility is unnecessary, all without retraining the base policy.

Jeanne Malécot, Hamed Rahimi, Jeanne Cattoni et al.

Existing human-robot interaction systems often lack mechanisms for sustained personalization and dynamic adaptation in multi-user environments, limiting their effectiveness in real-world deployments. We present HARMONI, a multimodal personalization framework that leverages large language models to enable socially assistive robots to manage long-term multi-user interactions. The framework integrates four key modules: (i) a perception module that identifies active speakers and extracts multimodal input; (ii) a world modeling module that maintains representations of the environment and short-term conversational context; (iii) a user modeling module that updates long-term speaker-specific profiles; and (iv) a generation module that produces contextually grounded and ethically informed responses. Through extensive evaluation and ablation studies on four datasets, as well as a real-world scenario-driven user-study in a nursing home environment, we demonstrate that HARMONI supports robust speaker identification, online memory updating, and ethically aligned personalization, outperforming baseline LLM-driven approaches in user modeling accuracy, personalization quality, and user satisfaction.

Hamed Rahimi, Clemence Grislain, Adrien Jacquet Cretides et al.

Improving the effectiveness of human-robot interaction requires social robots to accurately infer human goals through robust intention understanding. This challenge is particularly critical in multimodal settings, where agents must integrate heterogeneous signals including text, visual cues to form a coherent interpretation of user intent. This paper presents IntentVLM, a novel two-stage video-language framework designed for open-vocabulary human intention recognition. The approach is inspired by forward-inverse modeling in cognitive science by decomposing intention understanding into goal candidate generation followed by structured inference through selection, effectively reducing hallucinations in latent reasoning. Evaluated on the IntentQA and Inst-IT Bench datasets, IntentVLM achieves state-of-the-art results with up to 80% accuracy, notably surpassing the baseline performance by 30% and matches human performance. Our findings demonstrate that this structured reasoning approach enhances open-vocabulary intention understanding without catastrophic forgetting, offering a robust foundation for human-centered robotics.

Hamed Rahimi, Jeanne Cattoni, Meriem Beghili et al.

Personalization in social robotics is critical for fostering effective human-robot interactions, yet systems often face the cold start problem, where initial user preferences or characteristics are unavailable. This paper proposes a novel framework called USER-LLM R1 for a user-aware conversational agent that addresses this challenge through dynamic user profiling and model initiation. Our approach integrates chain-of-thought (CoT) reasoning models to iteratively infer user preferences and vision-language models (VLMs) to initialize user profiles from multimodal inputs, enabling personalized interactions from the first encounter. Leveraging a Retrieval-Augmented Generation (RAG) architecture, the system dynamically refines user representations within an inherent CoT process, ensuring contextually relevant and adaptive responses. Evaluations on the ElderlyTech-VQA Bench demonstrate significant improvements in ROUGE-1 (+23.2%), ROUGE-2 (+0.6%), and ROUGE-L (+8%) F1 scores over state-of-the-art baselines, with ablation studies underscoring the impact of reasoning model size on performance. Human evaluations further validate the framework's efficacy, particularly for elderly users, where tailored responses enhance engagement and trust. Ethical considerations, including privacy preservation and bias mitigation, are rigorously discussed and addressed to ensure responsible deployment.

Mohamed Salim Aissi, Clemence Grislain, Mohamed Chetouani et al.

While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this paper, we introduce VIPER, a novel framework for multimodal instruction-based planning that integrates VLM-based perception with LLM-based reasoning. Our approach uses a modular pipeline where a frozen VLM generates textual descriptions of image observations, which are then processed by an LLM policy to predict actions based on the task goal. We fine-tune the reasoning module using behavioral cloning and reinforcement learning, improving our agent's decision-making capabilities. Experiments on the ALFWorld benchmark show that VIPER significantly outperforms state-of-the-art visual instruction-based planners while narrowing the gap with purely text-based oracles. By leveraging text as an intermediate representation, VIPER also enhances explainability, paving the way for a fine-grained analysis of perception and reasoning components.

Louis Simon, Mohamed Chetouani

The widespread adoption of mobile and wearable sensing technologies has enabled continuous and personalized monitoring of affect, mood disorders, and stress. When combined with ecological self-report questionnaires, these systems offer a powerful opportunity to explore longitudinal modeling of human behaviors. However, challenges arise from missing data and the irregular timing of self-reports, which make challenging the prediction of human states and behaviors. In this study, we investigate the use of time embeddings to capture time dependencies within sequences of Ecological Momentary Assessments (EMA). We introduce a novel time embedding method, Ema2Vec, designed to effectively handle irregularly spaced self-reports, and evaluate it on a new task of longitudinal stress prediction. Our method outperforms standard stress prediction baselines that rely on fixed-size daily windows, as well as models trained directly on longitudinal sequences without time-aware representations. These findings emphasize the importance of incorporating time embeddings when modeling irregularly sampled longitudinal data.

Adil Bahaj, Oumaima Fadi, Mohamed Chetouani et al.

Large language models (LLMs) and vision-augmented LLMs (VLMs) have significantly advanced medical informatics, diagnostics, and decision support. However, these models exhibit systematic biases, particularly age bias, compromising their reliability and equity. This is evident in their poorer performance on pediatric-focused text and visual question-answering tasks. This bias reflects a broader imbalance in medical research, where pediatric studies receive less funding and representation despite the significant disease burden in children. To address these issues, a new comprehensive multi-modal pediatric question-answering benchmark, PediatricsMQA, has been introduced. It consists of 3,417 text-based multiple-choice questions (MCQs) covering 131 pediatric topics across seven developmental stages (prenatal to adolescent) and 2,067 vision-based MCQs using 634 pediatric images from 67 imaging modalities and 256 anatomical regions. The dataset was developed using a hybrid manual-automatic pipeline, incorporating peer-reviewed pediatric literature, validated question banks, existing benchmarks, and existing QA resources. Evaluating state-of-the-art open models, we find dramatic performance drops in younger cohorts, highlighting the need for age-aware methods to ensure equitable AI support in pediatric care.

Adil Bahaj, Hamed Rahimi, Mohamed Chetouani et al.

Recently, overconfidence in large language models (LLMs) has garnered considerable attention due to its fundamental importance in quantifying the trustworthiness of LLM generation. However, existing approaches prompt the \textit{black box LLMs} to produce their confidence (\textit{verbalized confidence}), which can be subject to many biases and hallucinations. Inspired by a different aspect of overconfidence in cognitive science called \textit{overprecision}, we designed a framework for its study in black box LLMs. This framework contains three main phases: 1) generation, 2) refinement and 3) evaluation. In the generation phase we prompt the LLM to generate answers to numerical questions in the form of intervals with a certain level of confidence. This confidence level is imposed in the prompt and not required for the LLM to generate as in previous approaches. We use various prompting techniques and use the same prompt multiple times to gauge the effects of randomness in the generation process. In the refinement phase, answers from the previous phase are refined to generate better answers. The LLM answers are evaluated and studied in the evaluation phase to understand its internal workings. This study allowed us to gain various insights into LLM overprecision: 1) LLMs are highly uncalibrated for numerical tasks 2) there is no correlation between the length of the interval and the imposed confidence level, which can be symptomatic of a a) lack of understanding of the concept of confidence or b) inability to adjust self-confidence by following instructions, {3) LLM numerical precision differs depending on the task, scale of answer and prompting technique 4) Refinement of answers doesn't improve precision in most cases. We believe this study offers new perspectives on LLM overconfidence and serves as a strong baseline for overprecision in LLMs.

Hamed Rahimi, Mouad Abrini, Mahdi Khoramshahi et al.

This paper investigates the performance of multimodal pre-trained models in user profiling tasks based on visual-linguistic demographic data. These models are critical for adapting to the needs and preferences of human users in social robotics, thereby providing personalized responses and enhancing interaction quality. First, we introduce two datasets specifically curated to represent demographic characteristics derived from user facial images. Next, we evaluate the performance of a prominent contrastive multimodal pre-trained model, CLIP, on these datasets, both in its out-of-the-box state and after fine-tuning. Initial results indicate that CLIP performs suboptimal in matching images to demographic descriptions without fine-tuning. Although fine-tuning significantly enhances its predictive capacity, the model continues to exhibit limitations in effectively generalizing subtle demographic nuances. To address this, we propose adopting a masked image modeling strategy to improve generalization and better capture subtle demographic attributes. This approach offers a pathway for enhancing demographic sensitivity in multimodal user modeling tasks.

Silvia Tulli, Stylianos Loukas Vasileiou, Mohamed Chetouani et al.

One of the significant challenges to generating value-aligned behavior is to not only account for the specified user objectives but also any implicit or unspecified user requirements. The existence of such implicit requirements could be particularly common in settings where the user's understanding of the task model may differ from the agent's estimate of the model. Under this scenario, the user may incorrectly expect some agent behavior to be inevitable or guaranteed. This paper addresses such expectation mismatch in the presence of differing models by capturing the possibility of unspecified user subgoal in the context of a task captured as a Markov Decision Process (MDP) and querying for it as required. Our method identifies bottleneck states and uses them as candidates for potential implicit subgoals. We then introduce a querying strategy that will generate the minimal number of queries required to identify a policy guaranteed to achieve the underlying goal. Our empirical evaluations demonstrate the effectiveness of our approach in inferring and achieving unstated goals across various tasks.

Hugo Caselles-Dupré, Mohamed Chetouani, Olivier Sigaud

When demonstrating a task, human tutors pedagogically modify their behavior by either "showing" the task rather than just "doing" it (exaggerating on relevant parts of the demonstration) or by giving demonstrations that best disambiguate the communicated goal. Analogously, human learners pragmatically infer the communicative intent of the tutor: they interpret what the tutor is trying to teach them and deduce relevant information for learning. Without such mechanisms, traditional Learning from Demonstration (LfD) algorithms will consider such demonstrations as sub-optimal. In this paper, we investigate the implementation of such mechanisms in a tutor-learner setup where both participants are artificial agents in an environment with multiple goals. Using pedagogy from the tutor and pragmatism from the learner, we show substantial improvements over standard learning from demonstrations.

Ramona Merhej, Fernando P. Santos, Francisco S. Melo et al.

Collective risk dilemmas (CRDs) are a class of n-player games that represent societal challenges where groups need to coordinate to avoid the risk of a disastrous outcome. Multi-agent systems incurring such dilemmas face difficulties achieving cooperation and often converge to sub-optimal, risk-dominant solutions where everyone defects. In this paper we investigate the consequences of risk diversity in groups of agents learning to play CRDs. We find that risk diversity places new challenges to cooperation that are not observed in homogeneous groups. We show that increasing risk diversity significantly reduces overall cooperation and hinders collective target achievement. It leads to asymmetrical changes in agents' policies -- i.e. the increase in contributions from individuals at high risk is unable to compensate for the decrease in contributions from individuals at low risk -- which overall reduces the total contributions in a population. When comparing RL behaviors to rational individualistic and social behaviors, we find that RL populations converge to fairer contributions among agents. Our results highlight the need for aligning risk perceptions among agents or develop new learning techniques that explicitly account for risk diversity.

Sebastian Wallkotter, Mohamed Chetouani, Ginevra Castellano

Robots that share an environment with humans may communicate their intent using a variety of different channels. Movement is one of these channels and, particularly in manipulation tasks, intent communication via movement is called legibility. It alters a robot's trajectory to make it intent expressive. Here we propose a novel evaluation method that improves the data efficiency of collected experimental data when benchmarking approaches generating such legible behavior. The primary novelty of the proposed method is that it uses trajectories that were generated independently of the framework being tested. This makes evaluation easier, enables N-way comparisons between approaches, and allows easier comparison across papers. We demonstrate the efficiency of the new evaluation method by comparing 10 legibility frameworks in 2 scenarios. The paper, thus, provides readers with (1) a novel approach to investigate and/or benchmark legibility, (2) an overview of existing frameworks, (3) an evaluation of 10 legibility frameworks (from 6 papers), and (4) evidence that viewing angle and trajectory progression matter when users evaluate the legibility of a motion.

Olivier Sigaud, Ahmed Akakzia, Hugo Caselles-Dupré et al.

Autonomous discovery and direct instruction are two distinct sources of learning in children but education sciences demonstrate that mixed approaches such as assisted discovery or guided play result in improved skill acquisition. In the field of Artificial Intelligence, these extremes respectively map to autonomous agents learning from their own signals and interactive learning agents fully taught by their teachers. In between should stand teachable autotelic agents (TAA): agents that learn from both internal and teaching signals to benefit from the higher efficiency of assisted discovery. Designing such agents will enable real-world non-expert users to orient the learning trajectories of agents towards their expectations. More fundamentally, this may also be a key step to build agents with human-level intelligence. This paper presents a roadmap towards the design of teachable autonomous agents. Building on developmental psychology and education sciences, we start by identifying key features enabling assisted discovery processes in child-tutor interactions. This leads to the production of a checklist of features that future TAA will need to demonstrate. The checklist allows us to precisely pinpoint the various limitations of current reinforcement learning agents and to identify the promising first steps towards TAA. It also shows the way forward by highlighting key research directions towards the design or autonomous agents that can be taught by ordinary people via natural pedagogy.

Giulia Perugia, Maike Paetzel-Prüssman, Isabelle Hupont et al.

In this paper, we present a study aimed at understanding whether the embodiment and humanlikeness of an artificial agent can affect people's spontaneous and instructed mimicry of its facial expressions. The study followed a mixed experimental design and revolved around an emotion recognition task. Participants were randomly assigned to one level of humanlikeness (between-subject variable: humanlike, characterlike, or morph facial texture of the artificial agents) and observed the facial expressions displayed by a human (control) and three artificial agents differing in embodiment (within-subject variable: video-recorded robot, physical robot, and virtual agent). To study both spontaneous and instructed facial mimicry, we divided the experimental sessions into two phases. In the first phase, we asked participants to observe and recognize the emotions displayed by the agents. In the second phase, we asked them to look at the agents' facial expressions, replicate their dynamics as closely as possible, and then identify the observed emotions. In both cases, we assessed participants' facial expressions with an automated Action Unit (AU) intensity detector. Contrary to our hypotheses, our results disclose that the agent that was perceived as the least uncanny, and most anthropomorphic, likable, and co-present, was the one spontaneously mimicked the least. Moreover, they show that instructed facial mimicry negatively predicts spontaneous facial mimicry. Further exploratory analyses revealed that spontaneous facial mimicry appeared when participants were less certain of the emotion they recognized. Hence, we postulate that an emotion recognition goal can flip the social value of facial mimicry as it transforms a likable artificial agent into a distractor.

Muhammad Muzammel, Hanan Salam, Yann Hoffmann et al.

Depression is a common and serious mood disorder that negatively affects the patient's capacity of functioning normally in daily tasks. Speech is proven to be a vigorous tool in depression diagnosis. Research in psychiatry concentrated on performing fine-grained analysis on word-level speech components contributing to the manifestation of depression in speech and revealed significant variations at the phoneme-level in depressed speech. On the other hand, research in Machine Learning-based automatic recognition of depression from speech focused on the exploration of various acoustic features for the detection of depression and its severity level. Few have focused on incorporating phoneme-level speech components in automatic assessment systems. In this paper, we propose an Artificial Intelligence (AI) based application for clinical depression recognition and assessment from speech. We investigate the acoustic characteristics of phoneme units, specifically vowels and consonants for depression recognition via Deep Learning. We present and compare three spectrogram-based Deep Neural Network architectures, trained on phoneme consonant and vowel units and their fusion respectively. Our experiments show that the deep learned consonant-based acoustic characteristics lead to better recognition results than vowel-based ones. The fusion of vowel and consonant speech characteristics through a deep network significantly outperforms the single space networks as well as the state-of-art deep learning approaches on the DAIC-WOZ database.

Ahmed Akakzia, Cédric Colas, Pierre-Yves Oudeyer et al.

We are interested in the autonomous acquisition of repertoires of skills. Language-conditioned reinforcement learning (LC-RL) approaches are great tools in this quest, as they allow to express abstract goals as sets of constraints on the states. However, most LC-RL agents are not autonomous and cannot learn without external instructions and feedback. Besides, their direct language condition cannot account for the goal-directed behavior of pre-verbal infants and strongly limits the expression of behavioral diversity for a given language input. To resolve these issues, we propose a new conceptual approach to language-conditioned RL: the Language-Goal-Behavior architecture (LGB). LGB decouples skill learning and language grounding via an intermediate semantic representation of the world. To showcase the properties of LGB, we present a specific implementation called DECSTR. DECSTR is an intrinsically motivated learning agent endowed with an innate semantic representation describing spatial relations between physical objects. In a first stage (G -> B), it freely explores its environment and targets self-generated semantic configurations. In a second stage (L -> G), it trains a language-conditioned goal generator to generate semantic goals that match the constraints expressed in language-based inputs. We showcase the additional properties of LGB w.r.t. both an end-to-end LC-RL approach and a similar approach leveraging non-semantic, continuous intermediate representations. Intermediate semantic representations help satisfy language commands in a diversity of ways, enable strategy switching after a failure and facilitate language grounding.

Cédric Colas, Ahmed Akakzia, Pierre-Yves Oudeyer et al.

In the real world, linguistic agents are also embodied agents: they perceive and act in the physical world. The notion of Language Grounding questions the interactions between language and embodiment: how do learning agents connect or ground linguistic representations to the physical world ? This question has recently been approached by the Reinforcement Learning community under the framework of instruction-following agents. In these agents, behavioral policies or reward functions are conditioned on the embedding of an instruction expressed in natural language. This paper proposes another approach: using language to condition goal generators. Given any goal-conditioned policy, one could train a language-conditioned goal generator to generate language-agnostic goals for the agent. This method allows to decouple sensorimotor learning from language acquisition and enable agents to demonstrate a diversity of behaviors for any given instruction. We propose a particular instantiation of this approach and demonstrate its benefits.

Anis Najar, Mohamed Chetouani

In this paper, we provide an overview of the existing methods for integrating human advice into a Reinforcement Learning process. We first propose a taxonomy of the different forms of advice that can be provided to a learning agent. We then describe the methods that can be used for interpreting advice when its meaning is not determined beforehand. Finally, we review different approaches for integrating advice into the learning process.

Karen Tatarian, Sebastian Wallkotter, Sera Buyukgoz et al.

The use of robots in educational settings is growing increasingly popular. Yet, many of the learning tasks involving social robots do not take full advantage of their physical embodiment. MobiAxis is a proposed learning task which uses the physical capabilities of a Pepper robot to teach the concepts of positive and negative multiplication along a number line. The robot is embodied with a number of multi-modal socially intelligent features and behaviours which are designed to enhance learning. This paper is a position paper describing the technical and theoretical implementation of the task, as well as proposed directions for future studies.

Sebastian Wallkotter, Silvia Tulli, Ginevra Castellano et al.

The issue of how to make embodied agents explainable has experienced a surge of interest over the last three years, and, there are many terms that refer to this concept, e.g., transparency or legibility. One reason for this high variance in terminology is the unique array of social cues that embodied agents can access in contrast to that accessed by non-embodied agents. Another reason is that different authors use these terms in different ways. Hence, we review the existing literature on explainability and organize it by (1) providing an overview of existing definitions, (2) showing how explainability is implemented and how it exploits different social cues, and (3) showing how the impact of explainability is measured. Additionally, we present a list of open questions and challenges that highlight areas that require further investigation by the community. This provides the interested reader with an overview of the current state-of-the-art.

Anis Najar, Olivier Sigaud, Mohamed Chetouani

In this paper, we propose a framework that enables a human teacher to shape a robot behaviour by interactively providing it with unlabeled instructions. We ground the meaning of instruction signals in the task-learning process, and use them simultaneously for guiding the latter. We implement our framework as a modular architecture, named TICS (Task-Instruction-Contingency-Shaping) that combines different information sources: a predefined reward function, human evaluative feedback and unlabeled instructions. This approach provides a novel perspective for robotic task learning that lies between Reinforcement Learning and Supervised Learning paradigms. We evaluate our framework both in simulation and with a real robot. The experimental results demonstrate the effectiveness of our framework in accelerating the task-learning process and in reducing the number of required teaching signals.

Pierre Fournier, Olivier Sigaud, Cédric Colas et al.

In this paper we study a new reinforcement learning setting where the environment is non-rewarding, contains several possibly related objects of various controllability, and where an apt agent Bob acts independently, with non-observable intentions. We argue that this setting defines a realistic scenario and we present a generic discrete-state discrete-action model of such environments. To learn in this environment, we propose an unsupervised reinforcement learning agent called CLIC for Curriculum Learning and Imitation for Control. CLIC learns to control individual objects in its environment, and imitates Bob's interactions with these objects. It selects objects to focus on when training and imitating by maximizing its learning progress. We show that CLIC is an effective baseline in our new setting. It can effectively observe Bob to gain control of objects faster, even if Bob is not explicitly teaching. It can also follow Bob when he acts as a mentor and provides ordered demonstrations. Finally, when Bob controls objects that the agent cannot, or in presence of a hierarchy between objects in the environment, we show that CLIC ignores non-reproducible and already mastered interactions with objects, resulting in a greater benefit from imitation.

Cédric Colas, Pierre Fournier, Olivier Sigaud et al.

In open-ended environments, autonomous learning agents must set their own goals and build their own curriculum through an intrinsically motivated exploration. They may consider a large diversity of goals, aiming to discover what is controllable in their environments, and what is not. Because some goals might prove easy and some impossible, agents must actively select which goal to practice at any moment, to maximize their overall mastery on the set of learnable goals. This paper proposes CURIOUS, an algorithm that leverages 1) a modular Universal Value Function Approximator with hindsight learning to achieve a diversity of goals of different kinds within a unique policy and 2) an automated curriculum learning mechanism that biases the attention of the agent towards goals maximizing the absolute learning progress. Agents focus sequentially on goals of increasing complexity, and focus back on goals that are being forgotten. Experiments conducted in a new modular-goal robotic environment show the resulting developmental self-organization of a learning curriculum, and demonstrate properties of robustness to distracting goals, forgetting and changes in body properties.

Pierre Fournier, Olivier Sigaud, Mohamed Chetouani et al.

In this paper, we investigate a new form of automated curriculum learning based on adaptive selection of accuracy requirements, called accuracy-based curriculum learning. Using a reinforcement learning agent based on the Deep Deterministic Policy Gradient algorithm and addressing the Reacher environment, we first show that an agent trained with various accuracy requirements sampled randomly learns more efficiently than when asked to be very accurate at all times. Then we show that adaptive selection of accuracy requirements, based on a local measure of competence progress, automatically generates a curriculum where difficulty progressively increases, resulting in a better learning efficiency than sampling randomly.

Ilaria Gaudiello, Elisabetta Zibetti, Sebastien Lefort et al.

To investigate the functional and social acceptance of a humanoid robot, we carried out an experimental study with 56 adult participants and the iCub robot. Trust in the robot has been considered as a main indicator of acceptance in decision-making tasks characterized by perceptual uncertainty (e.g., evaluating the weight of two objects) and socio-cognitive uncertainty (e.g., evaluating which is the most suitable item in a specific context), and measured by the participants' conformation to the iCub's answers to specific questions. In particular, we were interested in understanding whether specific (i) user-related features (i.e. desire for control), (ii) robot-related features (i.e., attitude towards social influence of robots), and (iii) context-related features (i.e., collaborative vs. competitive scenario), may influence their trust towards the iCub robot. We found that participants conformed more to the iCub's answers when their decisions were about functional issues than when they were about social issues. Moreover, the few participants conforming to the iCub's answers for social issues also conformed less for functional issues. Trust in the robot's functional savvy does not thus seem to be a pre-requisite for trust in its social savvy. Finally, desire for control, attitude towards social influence of robots and type of interaction scenario did not influence the trust in iCub. Results are discussed with relation to methodology of HRI research.

Serena Ivaldi, Sebastien Lefort, Jan Peters et al.

Estimating the engagement is critical for human - robot interaction. Engagement measures typically rely on the dynamics of the social signals exchanged by the partners, especially speech and gaze. However, the dynamics of these signals is likely to be influenced by individual and social factors, such as personality traits, as it is well documented that they critically influence how two humans interact with each other. Here, we assess the influence of two factors, namely extroversion and negative attitude toward robots, on speech and gaze during a cooperative task, where a human must physically manipulate a robot to assemble an object. We evaluate if the scores of extroversion and negative attitude towards robots co-variate with the duration and frequency of gaze and speech cues. The experiments were carried out with the humanoid robot iCub and N=56 adult participants. We found that the more people are extrovert, the more and longer they tend to talk with the robot; and the more people have a negative attitude towards robots, the less they will look at the robot face and the more they will look at the robot hands where the assembly and the contacts occur. Our results confirm and provide evidence that the engagement models classically used in human-robot interaction should take into account attitudes and personality traits.