Grenoble, France ; Paris, France

Join the conversation

I believe that with the advent of modern online collaboration platforms (such as Github), proof assistant languages (such as Lean), and (potentially) AI tools, there are many emerging opportunities...

Mapping conversation

A method for training our generalist policies with RL to improve success rate and throughput on real-world tasks.

In the past decade, motivated by the putative failure of naive self-play deep reinforcement learning (DRL) in adversarial imperfect-information games, researchers have developed numerous DRL algorithm...

YouTube video by Google DeepMind

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...

In Pittsburgh, I’m a professor at Carnegie Mellon University in the top computer science school in the world. I’ve also worked in various large technology companies, who have offices in Pittsburgh to connect with and employ Carnegie Mellon faculty and students.

New AI agent evolves algorithms for math and practical applications in computing by combining the creativity of large language models with automated evaluators

"social media" has always been oxymoronic

Researchers in “natural language processing” tried to tame human language. Then came the transformer.