• I recently defended my Ph.D. thesis entitled "Towards Social Autotelic Artificial Agents - Formation and Exploitation of Cultural Conventions in Autonomous Embodied Artificial Agents".
    Links: [Manuscript] [Presentation] [Slides]
  • I'm on the job market! I'm looking for research scientist, postdoc and researcher positions

Short Bio

I am an AI researcher holding a doctorate from the University of Bordeaux and Inria, where I conducted research in Developmental AI under the guidance of Clément Moulin-Frier and Pierre-Yves Oudeyer. Specifically, I explored how artificial agents can establish and leverage cultural conventions within Reinforcement Learning setups

Before pursuing my Ph.D., I worked on Natural Language Processing at PNB Paribas' innovation lab in New York. My academic background includes MSc degrees in machine learning from ISAE-Supaero and mechanical engineering from EPFL.

I am passionate about exploring the dynamic connections between language, culture, and AI. My professional goal is centered on applying my AI expertise to address real-world challenges, serving as a bridge between cutting-edge technology and societal needs.


Contrastive Multimodal Learning for Emergence of Graphical Sensory-Motor Communication
T. Karch*, Y. Lemesle*, R. Laroche, C. Moulin-Frier and P.Y. Oudeyer


Vygotskian Autotelic Artificial Intelligence: Language and Culture Internalization for Human-Like AI
Nature Machine Intelligence
Nature Machine Intelligence
C.Colas*, T. Karch*, C. Moulin-Frier and P.Y. Oudeyer


Learning to Guide and to Be Guided in the Architect-Builder Problem
ICLR 2022
B. Barde*, T. Karch*, D. Nowrouzezahrai, C. Moulin-Frier, C. Pal and P.Y. Oudeyer

[Paper][Website] [Presentation]

Grounding Spatio-Temporal Language with Transformer
NeurIPS 2021
NeurIPS 2021
T. Karch*, L. Teodorescu*, K. Hoffman, C. Moulin-Frier and P.Y. Oudeyer


Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration
NeurIPS 2020
NeurIPS 2020
C. Colas*, T. Karch*, N. Lair*, J.M. Dussoux, C. Moulin-Frier, P.F. Dominey and P.Y. Oudeyer


Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey
C. Colas, T. Karch, O. Sigaud and P.Y. Oudeyer


Deep Sets for Generalization in RL
ICLR 2020 BeTRL Workshop
ICLR 2020 BeTRL Workshop
T. Karch*, C. Colas*, L. Teodorescu, C. Moulin-Frier and P.Y. Oudeyer



Extracting Learning Signals from Social Contexts2024, January 10
Invited talk at ISIR - Sorbonne University, 2024, January 10


Learning to Guide and to Be Guided in the Architect-Builder Problem2022, January 14
RL Sofa at Mila, 2022, January 14


Vygotskian Autotelic Agents2021, July 26
Invited Talk at the Minds at Play! workshop of Cogsci 2021 , 2021, July 26


Word Representation for Natural Language Processing (Part 2)2019, February 22
BNP Paribas AI Lunch Talk in New York, 2019, February 22


Word Representation for Natural Language Processing (Part 1)2019, February 22
BNP Paribas AI Lunch Talk in New York , 2019, January 28


Blog Posts

Summary: Humans have an outstanding ability to teach and learn form each other without relying on pre-established communication protocol (not even expressing rewards). Could machine do the same? In this blog post we propose a new interactive learning paradigm to investigate this question.

Summary: This blog post presents a supra-communicative view of language and advocates for the use of language as a cognitive tool to organize the cognitive development of intrinsically motivated artificial agents. We go over studies revealing the cognitive functions of language in humans, cover similar uses of language in the design of artificial agents and advocate for the pursuit of Vygotskian embodied agents - artificial agents that leverage language as a cognitive tool to structure their continuous experience, form abstract representations, reason, imagine creative goals, plan towards them and simulate future possibilities.