Sign In
Get Clay Free →

Suggestions

    Natasha Jaques

    Incoming faculty at University of Washington, Senior Research Scientist at Google

    Natasha Jaques is an Assistant Professor at the Paul G. Allen School of Computer Science & Engineering at the University of Washington, where she began her position in January 2023. Her research primarily focuses on social reinforcement learning, multi-agent systems, and human-AI interaction, with the goal of improving how AI agents learn and collaborate through social learning techniques.12

    Education and Career

    • Ph.D. in Media Arts and Sciences from the Massachusetts Institute of Technology (MIT) in 2019.
    • M.Sc. in Computer Science from the University of British Columbia in 2014.
    • B.Sc. in Computer Science and B.A. in Psychology from the University of Regina, both completed in 2012.

    Before joining the University of Washington, Jaques was a Senior Research Scientist at Google Brain, where she explored the benefits of social learning in AI agents. She has also interned at DeepMind and Google Brain, and has experience mentoring as an OpenAI Scholars mentor.123

    Research Contributions

    Jaques's work has received recognition, including awards for Best Demo at NeurIPS and Best Paper at workshops focusing on machine learning applications in healthcare. Her research has been featured in prominent publications such as Science Magazine and MIT Technology Review. She is particularly interested in developing algorithms that enhance AI learning and generalization, focusing on how AI can learn from human interactions and from each other.123

    Publications and Impact

    Jaques has a significant number of citations for her work, indicating a strong influence in her field, particularly in areas related to reinforcement learning and AI collaboration. She actively publishes her research findings and contributes to the academic community through her work and mentorship.45

    For more detailed information about her research and publications, you can visit her professional website at natashajaques.ai or her LinkedIn profile here .23

    Highlights

    Jul 27 · twitter

    Excited to be speaking at the Montreal IVADO Bootcamp dedicated to Autonomous Agents, where I will give a remote talk on Multi-agent Reinforcement Learning for LLMs on August 15th at 11am ET.

    Full schedule and registration: https://t.co/28Hue8zKK7

    Jul 1 · twitter

    In our latest paper, we discovered a surprising result: training LLMs with self-play reinforcement learning on zero-sum games (like poker) significantly improves performance on math and reasoning benchmarks, zero-shot. Whaaat?

    How does this work? We analyze the results and find that LLMs learn emergent reasoning patterns like case-by-case analysis and expected value calculation that transfer to improve performance on math questions.

    This work shows the benefit of RL training for improving reasoning skills when there is no possibility for data leakage. AND how continuously evolving multi-agent competition leads to the development of emergent skills that generalize to novel tasks. Read more below!

    Mar 24 · youtube.com
    Social Reinforcement Learning with Natasha Jaques ... - YouTube
    Social Reinforcement Learning with Natasha Jaques ... - YouTube

    Related Questions

    What are some of Natasha Jaques' most notable research projects?
    How does Natasha Jaques' work on social reinforcement learning impact AI development?
    What awards has Natasha Jaques received for her research?
    Can you provide examples of Natasha Jaques' publications?
    What is Natasha Jaques' role at Google Brain?
    Natasha Jaques
    Natasha Jaques, photo 1
    Natasha Jaques, photo 2
    Add to my network

    Location

    Seattle, Washington, United States