Current Research
I am interested in unsupervised reinforcement learning (RL) algorithms that can capture the geometric structure of the world from experience, and utilize this knowledge to rapidly learn goal-directed behaviors.
|
|
Flattening Hierarchies with Policy Bootstrapping
John L. Zhou and Jonathan C. Kao
Preprint, 2025
project page /
paper /
code
We present Subgoal Advantage-Weighted Policy Bootstrapping (SAW), an offline goal-conditioned RL algorithm that achieves state-of-the-art performance on complex, long-horizon tasks without needing hierarchical policies or generative subgoal models.
|
|
Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents
John L. Zhou, Weizhe Hong, and Jonathan C. Kao
Advances in Neural Information Processing Systems, 2024
paper /
code
We propose a form of intrinsic motivation to reciprocate the influence of other agents’ actions on one’s own return, and show that this is sufficient to encourage mutual cooperation from other, self-interested agents in sequential social dilemmas.
|
|
Neuroscience Cloud Analysis As a Service
Taiga Abe et al. (Co-author)
Neuron, 2022
paper /
code
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
paper /
code
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.
|
|
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.
|
|
A Full Dive
John L. Zhou
Knowing Neurons, 2023
article
An article that takes a dive into the current state of brain-computer interfaces and open challenges in neural decoding and encoding. Inspired by my research as well as Sword Art Online, one of my favorite childhood anime series.
|
|