Oriol Vinyals
VP Of Research, Deep Learning Team Lead at DeepMind
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolOriol Vinyals is a VP of Research and Deep Learning Team Lead at Google DeepMind with 12+ years of experience advancing neural networks and reinforcement learning across text, speech, and vision. He led the AlphaStar effort that produced the first agent to beat a professional StarCraft player, and continues to blend foundational research with applied systems work. Previously a senior research scientist at Google Brain and a PhD candidate at UC Berkeley, he combines deep theoretical training with hands-on engineering. Oriol has contributed to influential open-source tooling such as the PySC2 StarCraft II learning environment, improving observations and multiplayer flexibility to help the RL community. Based in the Bay Area, he is known for pursuing both conceptual understanding and pragmatic improvements that accelerate research throughput.
12 years of coding experience
3 years of employment as a software developer
PhD, Electrical Engineering and Computer Science, PhD, Electrical Engineering and Computer Science at University of California, BerkeleyUniversity of California, San DiegoUPC Universitat Politècnica de Catalunya
Spanish, Catalan, English
Stackoverflow
1reputation
0reached
1answer
0questions
Github Skills (8)
machine-learning10
python10
reinforcement-learning10
numpy8
tensorflow7
lstm6
language-model6
softmax6
Programming languages (1)
Github contributions (5)
google-deepmind/pysc2
Sep 2017 - Jan 2019
StarCraft II Learning Environment
Role in this project:
ML Engineer
ML EngineerContributions:6 commits, 6 comments, 1 issue in 1 year 3 months
Contributions summary:Oriol primarily contributed to the PySC2 environment by making several improvements related to the handling of features and observations. They modified code to handle RGB image data, added camera position and size features, and allowed for independent raw resolution settings. Furthermore, the user refactored the environment step and added the ability to pass `disable_fog` in multiplayer, enhancing the environment's flexibility and functionality for reinforcement learning and StarCraft II interactions.
starcraftstarcraft-iiblizzard-apideep-learningreinforcement-learning
OriolVinyals/babel_main
Aug 2013 - Nov 2013
Contributions:20 commits in 3 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.