13,739 Hits in 9.0 sec

Multi-Agent Reinforcement Learning as a Computational Tool for Language Evolution Research: Historical Context and Future Challenges [article]

Clément Moulin-Frier, Pierre-Yves Oudeyer
2020 arXiv   pre-print
The goal of this paper is to position recent MARL contributions within the historical context of language evolution research, as well as to extract from this theoretical and computational background a  ...  Computational models of emergent communication in agent populations are currently gaining interest in the machine learning community due to recent advances in Multi-Agent Reinforcement Learning (MARL).  ...  A few theoretical contributions have proposed a potential role of curiosity-driven exploration in both language acquisition (Oller 2000) and evolution (Oudeyer and Smith 2015) .  ... 
arXiv:2002.08878v2 fatcat:x3xqoqiq2bclpfi2e2pxgt72vq

Application of the IBE-UNESCO Global Competences Framework in Assessing STEM-focused, Global Collaborative Learning Within a Digital Makerspace Environment

Danielle P. Espino, Seung B. Lee, Lauren Van Tress, Eric Hamilton
2019 International Conference on Computer Supported Collaborative Learning  
This is exemplified in the project as a willingness to learn through curiosity, creativity, critical thought, seen in devising projects, while curiosity and critical thinking are expressed through interactions  ...  Lifelong learning: The adaptive micro-competences include curiosity, creativity and critical thinking.  ...  In 2015, the United Nations adopted its 2030 Agenda for Sustainable Development, comprising 17 Sustainable Development Goals (SDGs) to address global social and economic issues.  ... 
dblp:conf/cscl/EspinoLT019 fatcat:5yrsq5vanne2rmok7yqjn7y3cq

Computational Theories of Curiosity-Driven Learning [article]

Pierre-Yves Oudeyer
2018 arXiv   pre-print
What are the functions of curiosity? What are the mechanisms of curiosity-driven learning?  ...  structures through curriculum learning.  ...  Curiosity-driven exploration through autonomous goal setting and self-organized curriculum learning in the experimental setup presented in [Forestier et al., 2017] (see video:  ... 
arXiv:1802.10546v2 fatcat:mtmud6nxk5afpdxsxwf6gub4z4

Building Human-like Communicative Intelligence: A Grounded Perspective

Marina Dubova
2021 Cognitive Systems Research  
development, and endowing the agents with adaptive feedback from their physical and social environment.  ...  I hope that these ideas can direct AI research towards building machines that develop human-like language abilities through their experiences with the world.  ...  PCL, EASy, and Building a Mind lab meetings for their valuable comments on the earlier versions of this manuscript.  ... 
doi:10.1016/j.cogsys.2021.12.002 fatcat:c2dwpl43dba2dduhmbm4fg2ayy

Introduction to the Special Issue on Machine Learning for Multiple Modalities in Interactive Systems and Robots

Heriberto Cuayáhuitl, Lutz Frommberger, Nina Dethlefs, Antoine Raux, Mathew Marge, Hendrik Zender
2014 ACM transactions on interactive intelligent systems (TiiS)  
This special issue highlights research articles that apply machine learning to robots and other systems that interact with users through more than one modality, such as speech, gestures, and vision.  ...  However, machine learning methods that encompass multiple modalities of an interactive system are still relatively hard to find.  ...  ACKNOWLEDGMENTS We thank the chief editors of ACM TiiS, Anthony Jameson, John Riedl and Krzysztof Gajos, for letting this special issue become a reality and for their high commitment with this journal.  ... 
doi:10.1145/2670539 fatcat:mpwlonu2yfcnher33owzkl6j6y

Open challenges in understanding development and evolution of speech forms: The roles of embodied self-organization, motivation and active exploration

Pierre-Yves Oudeyer
2015 Journal of Phonetics  
In particular, we emphasize the importance of embodied self-organization , as well as the role of mechanisms of motivation and active curiosity-driven exploration in speech formation.  ...  This article discusses open scientific challenges for understanding development and evolution of speech forms, as a commentary to Moulin-Frier et al. (Moulin-Frier et al., 2015).  ...  For example, an open question is to understand how an intrinsically motivated learner that discovers speech sounds through curiosity--driven exploration and/or through a social process for sharing emotions  ... 
doi:10.1016/j.wocn.2015.09.001 fatcat:zwjgd3tbnvfz7fodancabckfru

Curiosity-driven phonetic learning

Clement Moulin-Frier, Pierre-Yves Oudeyer
2012 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)  
robotics motor learning problem, exploration, random goal selection with reaching, and curiosity- that of learning the inverse model mapping a distribution of driven active goal selection with reaching  ...  Curiosity-driven phonetic learning. ICDL-Epirob - International Conference on Development and Learning, Epirob, Nov 2012, San Diego, United States. 2012.  ... 
doi:10.1109/devlrn.2012.6400583 dblp:conf/icdl-epirob/Moulin-FrierO12 fatcat:skmbheac6zgwfmgtsi6yxmvlhq

Motivation-driven educational game design

Guillaume Denis, Pierre Jouvelot
2005 Proceedings of the 2005 ACM SIGCHI International Conference on Advances in computer entertainment technology - ACE '05  
Its overall pedagogical goal is to spur the players' curiosity and creativity by enabling them to easily play music using gamepads as musical instruments.  ...  Building upon research on motivation theory, we provide insights on how video games can be framed as expert tools that naturally reconcile learning and fun, a worthy goal since students are forced to where  ...  Looking at motivation through the impact of challenges and skills, we introduce, building on Novak's work on flow 1 [15] , the notion of parallelism between fun and learning: curiosity and proficiency  ... 
doi:10.1145/1178477.1178581 dblp:conf/ACMace/DenisJ05 fatcat:svf3c5zj5rbmnkyi5hx2a2lqbe

SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents [article]

Grgur Kovač, Rémy Portelas, Katja Hofmann, Pierre-Yves Oudeyer
2021 arXiv   pre-print
Within the Deep Reinforcement Learning (DRL) field, this objective motivated multiple works on embodied language use.  ...  In this paper, we argue that aiming towards human-level AI requires a broader set of key social skills: 1) language use in complex and variable social contexts; 2) beyond language, complex embodied communication  ...  Acknowledgments This work was supported by Microsoft Research through its PhD Scholarship Programme.  ... 
arXiv:2107.00956v3 fatcat:6jyi3eivtfctbl2vl66se2jy3q

Object Learning Through Active Exploration

Serena Ivaldi, Sao Mai Nguyen, Natalia Lyubova, Alain Droniou, Vincent Padois, David Filliat, Pierre-Yves Oudeyer, Olivier Sigaud
2014 IEEE Transactions on Autonomous Mental Development  
The robot actively explores the objects through manipulation, driven by a combination of social guidance and intrinsic motivation.  ...  interaction scenario inspired by social parenting.  ...  Researchers leverage these insights to make robots learn objects and concepts through active exploration and social interaction.  ... 
doi:10.1109/tamd.2013.2280614 fatcat:3376fjdbczbypjhag625cwkssu

Towards Teachable Autotelic Agents [article]

Olivier Sigaud and Ahmed Akakzia and Hugo Caselles-Dupré and Cédric Colas and Pierre-Yves Oudeyer and Mohamed Chetouani
2022 arXiv   pre-print
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.  ...  Building on developmental psychology and education sciences, we start by identifying key features enabling assisted discovery processes in child-tutor interactions.  ...  This project has partly received funding from the European Union's Horizon 2020 research and innovation programmes under grant agreement No 761758 (HumanE AI NET) and No 765955 (ANIMATAS).  ... 
arXiv:2105.11977v2 fatcat:w37mjxeaafefnko3a64on7l3uu

Computational and Robotic Models of Early Language Development: A Review [article]

Pierre-Yves Oudeyer, George Kachergis, William Schueller
2019 arXiv   pre-print
Keywords: Early language learning, Computational and robotic models, machine learning, development, embodiment, social interaction, intrinsic motivation, self-organization, dynamical systems, complexity  ...  We then discuss their role in understanding several key mechanisms of language development: cross-situational statistical learning, embodiment, situated social interaction, intrinsically motivated learning  ...  Early language acquisition driven by curiosity.  ... 
arXiv:1903.10246v1 fatcat:p6oxxjuqjrbfllot44e5tbiirq

Being in Uncertainties: An Inquiry-based Model Leveraging Complexity in Teaching-Learning

Diane Rosen, State University of New York, Suffern
2019 Northeast Journal of Complex Systems  
Education is traditionally structured as a closed system, privileging result-driven methods that offer control and predictability.  ...  Narrowing the broad implications of a complexity lens on education, this paper focuses on generative uncertainty in teaching-learning, a paradoxical state of epistemological and creative growth described  ...  Grounded in the spirit of what makes us want to learn, MoI emphasized intrinsic motivation like natural curiosity over necessary, but often less effective, extrinsic goals like knowing answers for an exam  ... 
doi:10.22191/nejcs/vol1/iss1/5 fatcat:jbn4g3vk3nas3mqxr7jqsd5hpa

Controlling Synthetic Characters in Simulations: A Case for Cognitive Architectures and Sigma [article]

Volkan Ustun, Paul S. Rosenbloom, Seyed Sajjadi, Jeremy Nuttal
2021 arXiv   pre-print
reinforcement learning models in; (2) A pair of adaptive and interactive agent models that demonstrate rule-based, probabilistic, and social reasoning; and (3) A knowledge-free exploration model in which  ...  that are perceptual, autonomous, interactive, affective, and adaptive.  ...  Statements and opinions expressed do not necessarily reflect the position or the policy of the United States Government, and no official endorsement should be inferred.  ... 
arXiv:2101.02231v1 fatcat:e5hafvc3xjcjda4jeqruyuelmi

Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration [article]

Cédric Colas, Tristan Karch, Nicolas Lair, Jean-Michel Dussoux, Clément Moulin-Frier, Peter Ford Dominey, Pierre-Yves Oudeyer
2020 arXiv   pre-print
In addition, we identify the properties of goal imagination that enable these results and study the impacts of modularity and social interactions.  ...  Such imaginative agents, like children, benefit from the guidance of a social peer who provides language descriptions.  ...  Acknowledgments and Disclosure of Funding Cédric Colas and Tristan Karch are partly funded by the French Ministère des Armées -Direction Générale de l'Armement.  ... 
arXiv:2002.09253v4 fatcat:ygwwtst7rrfpppl6zjxijunbwu
« Previous Showing results 1 — 15 out of 13,739 results