Home

Hi! I'm Cédric Colas, AI researcher and digital tinkerer.

Research Interests

I’m interested in the study of artificial open-ended skill discovery, the ability for an artificial agent to grow an open-ended repertoire of skills along its life. This led me to focus on intrinsically motivated agents that set their own goals, autotelic agents.

I’m also convinced that to develop such abilities, agents will need to be immersed into rich socio-cultural worlds, to interact with their peers and with humans, to participate in a shared cultural evolution, with us. This idea is developed in our perspective article.

I’ve obtained my PhD at the Flowers Lab under the supervision of Pierre-Yves Oudeyer and Olivier Sigaud. The title of the thesis is Towards Vygotskian Autotelic Agents: Learning Skills with Goals, Language and Intrinsically Motivated Deep Reinforcement Learning (manuscript, defense).

I’m currently working with Joshua Tenenbaum and Jacob Andreas at MIT, where I develop autotelic agents able to learn from humans and others using program synthesis methods.

Tinkering

I often think of ways to reuse the algorithms I encounter in my research for alternative mostly useless purposes. This leads to the projects presented here.

Acknowledgment

The website robot logo is modified from a Flaticon logo, created by Slidesgo.