I am a senior research scientist in the Google DeepMind team in Paris. Before that, I was very lucky to be an AI resident in the Google Brain team in Montréal.

I am interested in leveraging human feedback for sequential decision making. This led me to explore ideas related to distributional RL, imitation learning, offline RL, and RL from human feedback. I am very proud to be a contributor of the Acme library.

In late 22/early 23, I built the RLHF layer of Bard. I am currently leading the post-training development of Gemma models.

contact: robert (dot) dadashi (at) gmail (dot) com