PeopleofSuperintelligence

Researcher

David Abel

David Abel is a reinforcement learning researcher at DeepMind whose work examines the foundations of agency, learning and computation. A Carleton College graduate in computer science and philosophy, he earned a PhD in computer science at Brown University in 2020 under Michael Littman, with a dissertation on abstraction in reinforcement learning. In September 2020 he joined DeepMind in London, and his paper On the Expressivity of Markov Reward, written with Will Dabney, Anna Harutyunyan, Mark Ho, Michael Littman, Doina Precup and Satinder Singh, won a NeurIPS 2021 Outstanding Paper Award. Later papers include Settling the Reward Hypothesis and A Definition of Continual Reinforcement Learning in 2023 and General Agents Contain World Models in 2025. He moved to Edinburgh in 2024, and he is a Staff Research Scientist on DeepMind's Agency team and an Honorary Fellow at the University of Edinburgh.

Badges

Timeline

  1. By 2020

    Carleton and a Brown PhD

    After an undergraduate degree in computer science and philosophy at Carleton College, he earns a master's in philosophy through Brown's Open Graduate Education program and a computer science PhD at Brown in 2020 under the supervision of Michael Littman. In 2019, he is one of four graduate students to win Brown's Presidential Award for Excellence in Teaching.

  2. April 2020

    A thesis on abstraction

    He completes his PhD in April 2020 with the dissertation A Theory of Abstraction in Reinforcement Learning. It offers three desiderata for abstraction functions: preserve representation of near-optimal behavior, be learned and constructed efficiently, and lower planning or learning time. It then presents new algorithms and analysis on how agents can learn to abstract along those lines.

  3. September 2020

    Joining DeepMind in London

    In September 2020, he moves to London and joins DeepMind as a Research Scientist. He had interned at DeepMind during the summer before his final year at Brown.

  4. 2021

    NeurIPS Outstanding Paper Award

    On the Expressivity of Markov Reward, which he writes with Will Dabney, Anna Harutyunyan, Mark K. Ho, Michael Littman, Doina Precup and Satinder Singh, wins a NeurIPS 2021 Outstanding Paper Award, one of six chosen from more than 9,000 submissions. The paper shows that some tasks have no Markov reward function that induces them, and that deciding in polynomial time whether a compatible Markov reward exists is possible.

  5. 2022

    A dissertation award runner-up

    In March 2022, Brown's computer science department announces him as one of two runners-up for the 2020 Joint AAAI/ACM SIGAI Doctoral Dissertation Award, recognizing his dissertation on abstraction in reinforcement learning.

  6. 2023

    Reward and continual learning

    In 2023, he co-authors Settling the Reward Hypothesis (ICML 2023) with Michael Bowling, John D. Martin and Will Dabney, which specifies the requirements on goals and purposes under which the reward hypothesis holds. He also co-authors A Definition of Continual Reinforcement Learning (NeurIPS 2023) with André Barreto, Benjamin Van Roy, Doina Precup, Hado van Hasselt and Satinder Singh, which defines the setting in which the best agents never stop learning.

  7. 2024

    Moving to Edinburgh

    He moves to Edinburgh, Scotland, in March 2024 and starts as an Honorary Fellow at the University of Edinburgh in September 2024. For RLC 2024, he co-authors Three Dogmas of Reinforcement Learning with Mark Ho and Anna Harutyunyan.

  8. As of October 2026

    Staff research scientist at DeepMind

    In 2025, he co-authors General Agents Contain World Models with Jonathan Richens, Alexis Bellot and Tom Everitt, which shows that any agent capable of generalizing to multi-step goal-directed tasks must have learned a predictive model of its environment. He is a Staff Research Scientist at DeepMind on the Agency team and an Honorary Fellow at the University of Edinburgh, with research on the foundations of agency, learning and computation. He is also Program Chair for RLDM 2027.

Career

  1. Since 2024University of EdinburghHonorary Fellow
  2. Since 2020Google DeepMindIntern

Education

  1. 2020Brown UniversityMaster's in philosophy
  2. Carleton CollegeUndergraduate degree in computer science and philosophy

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes David Abel. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. Google had the most people shaping AI every year from 2014 to 2025Includes Google. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  3. Google has the highest combined h-index among AI organizationsIncludes Google. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  4. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Google. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of David Abel yet. Send us a free-licensed photo.

  1. Alum Profile: David Abel '20 PhD | Graduate School | Brown University graduateschool.brown.edu. Checked 21 October 2026.
  2. David Abel | Simons Institute for the Theory of Computing simons.berkeley.edu. Checked 21 October 2026.
  3. David Abel Wins A Presidential Award For Excellence In Teaching cs.brown.edu. Checked 21 October 2026.
  4. A Theory of Abstraction in Reinforcement Learning arxiv.org. Checked 21 October 2026.
  5. David Abel david-abel.github.io. Checked 21 October 2026.
  6. Brown CS Alums David Abel And Mark K. Ho, Professor Michael Littman, And Collaborators Win A NeurIPS Outstanding Paper Award awards.cs.brown.edu. Checked 21 October 2026.
  7. Announcing the NeurIPS 2021 Award Recipients blog.neurips.cc. Checked 21 October 2026.
  8. Brown CS Alum David Abel Is A Joint AAAI/ACM SIGAI Doctoral Dissertation Award Runner-Up cs.brown.edu. Checked 21 October 2026.
  9. Settling the Reward Hypothesis arxiv.org. Checked 21 October 2026.
  10. A Definition of Continual Reinforcement Learning arxiv.org. Checked 21 October 2026.
  11. General agents contain world models arxiv.org. Checked 21 October 2026.