Until recently, Research Engineer at Meta. Now temporarily funemployed, updates coming soon. PhD from École Polytechnique, my thesis topic was "Simulating Crowds with Reinforcement Learning". In the past I was at University of Warsaw, KTH Royal Institute of Technology, and Aalto University.

Back in the day I was maintaining Gymnasium (the official continuation of OpenAI Gym), sometimes reviewing other people's bugs, sometimes adding my own bugs... I mean, features. Sometimes I also helped with PettingZoo, SuperSuit and other projects in the Farama Foundation.

My two main personal projects are Coltra, which was a "classic" RL library I mostly used for my PhD and random other experiments; and gyllm, which is a gym(nasium)-inspired API for LLM RL envs, with some simple single-GPU algorithms included.

Erdős number <= 4