Scholar
David Abel
Google Scholar ID: lvBJlmwAAAAJ
DeepMind / University of Edinburgh
Citations & Impact
Citations
2,062
H-index
22
i10-index
31
Publications
20
Co-authors
79
list available
Publications
Cited
0
Resume (English only)
Academic Achievements
- Published multiple papers, including 'Plasticity as the Mirror of Empowerment' (NeurIPS 2025), 'General Agents Contain World Models' (ICML 2025), 'Three Dogmas of Reinforcement Learning' (RLC 2024), 'A Definition of Continual Reinforcement Learning' (NeurIPS 2023), 'Settling the Reward Hypothesis' (ICML 2023), 'People Construct Simplified Mental Representations to Plan' (Nature 2022), 'On the Expressivity of Markov Reward' (NeurIPS 2021, Outstanding Paper Award), 'The Value of Abstraction' (Current Opinions in Behavioral Science 2019), 'Finding Options that Minimize Planning Time' (ICML 2019).
Research Experience
- Works at DeepMind's Agency team; supports students in the MARBLE group at the University of Edinburgh; collaborates with researchers such as Michael Bowling, André Barreto, Will Dabney, and others.
Education
- Ph.D. Thesis: 'A Theory of Abstraction in Reinforcement Learning', advised by Michael L. Littman, 2020.
Background
- A Staff Research Scientist at DeepMind on the Agency team and an Honorary Fellow at the University of Edinburgh. His research focuses on understanding the foundations of agency, learning, and computation, particularly in reinforcement learning, drawing on tools and perspectives from philosophy, math, and computer science.
Miscellany
- Excited by fundamental questions, philosophical depth, and clarity. Currently interested in developing the scientific bedrock of agency.
