Junhyuk Oh

I'm a co-founder of Ineffable Intelligence. I'm interested in building agents that learn from experience and scalable algorithms through which intelligence can emerge.

Before Ineffable Intelligence, I was a senior staff research scientist at Google DeepMind. I received my Ph.D. from the University of Michigan, where I was advised by Honglak Lee and Satinder Singh.

I go by Jun pronounced like the month “June”

Junhyuk Oh smiling against a warm neutral background

News

Invited talks

Selected work

  1. 2025Discovering state-of-the-art reinforcement learning algorithmsNature
  2. 2023Gemini: A Family of Highly Capable Multimodal ModelsTechnical report
  3. 2020Discovering Reinforcement Learning AlgorithmsNeurIPS
  4. 2019Grandmaster level in StarCraft II using multi-agent reinforcement learningNature
  5. 2017Value Prediction NetworkNeurIPS
More on Google Scholar