Hello! I am Tristan Karch, a Ph.D. student at Inria in the Flowers team under the supervision of Pierre-Yves Oudeyer and Clément Moulin-Frier. I am working on Grounding Language Agents and Curiosity-driven exploration.

Short Bio

I have a diverse academic background ranging from Mechanical Engineering to Machine Learning. I started by completing a BSc and MSc at Ecole Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, where I specialized in Computational Fluid Dynamics (CFD) and Computational Science. I also followed a joint master’s degree program with the Institut Supérieur de l’Aéronautique et de l’Espace (ISAE-Supaero) in Toulouse, France and graduated from the Data and Decision Sciences progam.

After my studies I moved to New York to join the Innovation Lab of BNP Paribas, a major french bank. I was working on implementing state of the art Natural Language Processing models in order to understand legal language.

Since october 2019, I joind the Flowers team at Inria Bordeaux as a PhD sutdent under the supervision of Pierre-Yves Oudeyer.


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

NeurIPS 2020

C. Colas*, T. Karch*, N. Lair*, J.M. Dussoux, C. Moulin-Frier, P.F. Dominey and P.Y. Oudeyer

[Paper] [Code] [Colab] [Blog Post]

Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey

Under review

C. Colas, T. Karch, O. Sigaud and P.Y. Oudeyer


Language-Goal Imagination to Foster Creative Exploration in Deep RL

ICML 2020 Language in Reinforcement Learning Workshop

T. Karch*, N. Lair*, C. Colas*, J.M. Dussoux, C. Moulin-Frier, P.F. Dominey and P.Y. Oudeyer


Deep Sets for Generalization in RL

ICLR 2020 BeTRL Workshop

T. Karch*, C. Colas*, L. Teodorescu, C. Moulin-Frier and P.Y. Oudeyer


Blog Posts

Language as a Cognitive Tool: Dall-E, Humans and Vygotskian RL Agents

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.