Written after watching Mulholland Drive, in memory of David Lynch.
I successfully defended my thesis on Friday, June 30, 2023! What an epic conclusion to this amazing eight-year journey.
An attempt at a "pointing-out" instruction, intended to reveal the nature of mind, built up starting from as few distinct words as possible.
An overview of our NeurIPS 2021 paper on learning state abstractions for RL that provably preserve the Markov property.
An overview of our IJCAI 2021 paper on efficient black-box planning by discovering and using macro-actions that modify only a small number of state variables.
A few short, paradoxical writings intended to somehow reveal a deeper truth than words can hope to express.
Notes from reading three papers on the geometry of value functions in reinforcement learning.
An essay I wrote after reading (just the preface to) Gödel, Escher, Bach and then falling into a tangled conversation about it.
Notes from my recent attempt to understand group theory and how it relates to learning disentangled representations.
My perspective on the core problems artificial intelligence, viewed through the lens of reinforcement learning.
An essay I wrote in the spring of 2018 on the history of AI for playing board games.