ÂÜÀòÂÒÂ×

Adrien Ecoffet is a Research Scientist with OpenAI, where they study emergent behaviors in multi-agent reinforcement learning. Adrien is a co-first author of a published article titled "First return, then explore," which has been covered by media outlets such as New Scientist, Scientific American, and the BBC. Prior to joining OpenAI, Adrien was a Research Scientist with Uber, where they continued their work on exploration in RL, led the development of the deep RL algorithm "Go-Explore," and solved the grand-challenge Atari game "Montezuma's Revenge." Earlier in their career, Adrien worked as a Staff Software Engineer (Machine Learning) and a Software Engineer (Product and ML) with Quora, where they implemented several core parts of the ads system and built search-related products. Adrien holds engineering internship experience with companies like Asobo Studio and Wopata.

Adrien Ecoffet completed their Bachelor of Science in Computer Engineering at the European Institute of Technology (EPITECH) from 2009 to 2013. In 2013, they spent a semester as an exchange student at UC San Diego, studying Computer Science. Adrien later earned their Master of Science in Computer Science from the Georgia Institute of Technology in 2018.