Scholar

Robert Dadashi

Google Scholar ID: RWyPeYYAAAAJ

Google DeepMind

Reinforcement Learning

Citations & Impact

All-time

Citations

11,922

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Research Experience

Between 2019 and 2022, led fundamental research on distributional RL, imitation learning, offline RL, and RL from human feedback, and contributed to the Acme library; In late 22/early 23, built the RLHF layer of the first version of Bard (now "Gemini App"); Since late 23, leading post-training of Gemma models which includes Gemma 1, Gemma 2, Gemma 3, Gemma 3n; In early 2025, led post-training of Gemini Nano v3, a model optimized for on-device use cases (powering the Pixel 10).

Background

Senior Staff Research Scientist in the Google DeepMind team in Paris. Research interests include distributional RL, imitation learning, offline RL, and RL from human feedback.

Co-authors

7 total