Joey Hejna

(Donald Joseph Hejna III)

I'm a fourth year student at UC Berkeley studying electrical engineering and computer science. Currently, I work with Professors Lerrel Pinto and Pieter Abbeel on reserach related to reinforcement learning and robotics. My legacy website can be found here.

jhejna @ berkeley.edu  /  Resume  /  Github  /  LinkedIn

• Our paper on unsupervised morphology optimization was accepted at ICLR 2021.
• I was recognized as an honorable mention for the CRA Outstanding Undergraduate Researcher Award

I'm broadly interested in learning for intelligent systems.

We propose transferring RL policies across agents using a hierarchical framework. Then, to remedy poor zero-shot transfer performance we introduce two additional imitation objectives.

Better robot strucutres hold the promise of better performance. We propose a new algorithm, TAME, that is able to evolve morphologies without any task specification. This is accomplished using an information theoretic objective that efficiently ranks morphologies based on their ability to explore and control their environment.

We examine and compare three methods for explicitly disentangling learned latent representations in VAE models.

Developed C++ systems for trading APIs and monitoring systems. Worked on optimizing memory usage of large model training.

Worked on demo systems for Intel's OpenVino model optimization system in the AWS DeepLens. Explored systems for gradient based explanations of deep networks.

Website source taken from here.