Biography

I’m a PhD student with the NYU Center for Data Science, advised by Brenden Lake and Todd Gureckis. My research interests center around cognitively-inspired machine learning: how can we draw inspiration from human cognition to advance the design of machine learning methods. I am particularly interested in studying the compositional space of tasks humans operate in and using cognitively-driven task representations to improve exploration in reinforcement learning. I am also very excited about the role of objects in reinforcement learning and object-centric reasoning.

In my non-academic life, I enjoy playing ultimate frisbee, making homemmade fermented hot sauces, and making friends with all of the puppies in Brooklyn.

Interests
  • Cognitive representations of tasks and games
  • Exploration, generalization, and task-conditioned RL
  • Object representations and object-centric reasoning
Education
  • PhD in Data Science, 2019--

    New York University

  • BSc in Computational Sciences, 2015--2019

    Minerva University

Recent Publications

(2022). Creativity, Compositionality, and Common Sense in Human Goal Generation. Proceedings of the 44th Annual Meeting of the Cognitive Science Society, CogSci 2022.

Cite URL

(2021). Examining Infant Relation Categorization Through Deep Neural Networks. Proceedings of the 43rd Annual Meeting of the Cognitive Science Society, CogSci 2021.

PDF Cite URL

(2021). A model of mood as integrated advantage. Psychological Review.

PDF Cite DOI URL

(2020). Investigating Simple Object Representations in Model-Free Deep Reinforcement Learning. Proceedings of the 42nd Annual Meeting of the Cognitive Science Society, CogSci 2020.

PDF Cite arXiv

(2020). Systematically Comparing Neural Network Architectures in Relation Learning. Object-Oriented Learning (OOL): Perception, Representation, and Reasoning Workshop at ICML 2020.

Cite URL

(2020). Sequential mastery of multiple visual tasks: Networks naturally learn to learn and forget to forget . The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

PDF Cite arXiv URL

(2019). Contrasting the effects of prospective attention and retrospective decay in representation learning. The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making.

PDF Cite

(2019). Momentum and mood in policy-gradient reinforcement learning. The 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making.

PDF Cite

Summer Schools

Brains, Minds, and Machines Summer Course
Attended the 2021 Brains, Minds, and Machines summer course in Woods Hole, MA.
Machine Learning Summer School
Attended the July 2019 MLSS in London, England.