Current Research
I am broadly interested in general-purpose agents who can acquire useful representations and skills without external supervision. My goal is to endow autonomous agents with an intrinsic sense of curiosity that drives them to explore and influence the world around them.
|
|
Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents
John L. Zhou, Weizhe Hong, and Jonathan C. Kao
Advances in Neural Information Processing Systems (NeurIPS), 2024
arXiv /
code /
We introduce an intrinsic reciprocal reward that encourages an agent to reciprocate the influence of other agents’ actions on its own return, and show that this encourages cooperation from other self-interested agents in sequential social dilemmas.
|
|
Neuroscience Cloud Analysis As a Service
Taiga Abe et al. (Co-author)
Neuron, 2022
code /
paper /
An open-source, drag-and-drop platform that uses cloud resources to run modern neuroscience data analyses.
|
|
Partitioning variability in animal behavioral videos using semi-supervised variational autoencoders
Matthew R Whiteway et al. (Co-author)
PLOS Computational Biology, 2021
code /
paper /
A semi-supervised framework that combines the output of supervised pose estimation algorithms with unsupervised dimensionality reduction methods to produce interpretable, low-dimensional representations of behavioral videos.
|
Previous Research
My previous work in other fields.
|
|
A Requirement of Protein Geranylgeranylation for Chemokine Receptor Signaling and Th17 Cell Function in an Animal Model of Multiple Sclerosis
Gregory Swan et al. (Co-author)
Frontiers in Immunology, 2021
paper /
We elucidate the critical role of protein geranylgeranylation in regulating T lymphocyte migration and function.
|
|