I'm a Ph.D candidate in Computer Science at Brown University focusing on Artificial Intelligence, advised by Prof. Michael Littman.
My research investigates the foundations of Artificial Intelligence and applications thereof to scientific and societal challenges.
In my current work, I study how intelligent agents model the worlds they inhabit, focusing on the representational practices that underly effective learning and planning. In these endeavors I value simple mathematical models with high explanatory power that allow for reproducible empirical inquiry. To these ends, I typically work with the Reinforcement Learning paradigm, drawing on tools from computational learning theory, probability, complex systems, and information theory.
I also care deeply about responsible applications of AI to problems of relevance in the world, with a current focus on the mission of computational sustainability.
Bandit-Based Solar Panel Control
David Abel, Edward C. Williams, Stephen Brawner, Emily Reif, Michael L. Littman
We advocate for the use of bandit methods for solar tracking and control and verify that a bandit-based approach can increase energy harvested compared to typical solar trackers.
Toward Good Abstractions for Lifelong Learning
David Abel, Dilip Arumugam, Lucas Lehnert, Michael L. Littman
NIPS 2017 Workshop on Hierarchical Reinforcement Learning
We provide a collection of results on lifelong RL with state and action abstractions, suggesting pathways for defining good abstractions.
Full list of papers here.
For fun, I'm a big fan of basketball, hiking, travel, fitness, cooking, snowboarding, and music (especially folk, trance, and progressive metal).
I'm an advocate of a few specific causes: sustainability efforts, existential risk minimization, space exploration, and improving the diversity, quality, and accessibility of STEM education.
Always up for a chat, and happy to visit labs or companies to give talks - shoot me an email if you'd like to discuss further!