Bill Zheng

I'm an incoming PhD student at UT Austin studying computer science, where my research will be supported by an NSF Graduate Research Fellowship. Currently, I am a research scientist intern at NVIDIA's General Embodied Agent Research (GEAR) group.

I completed my undergraduate degree in EECS at UC Berkeley, where I am grateful to be advised by Professor Sergey Levine at Robotics, AI, and Learning Lab. I am also fortunate to work with Professor Kuan Fang and Professor Benjamin Eysenbach. I'm broadly interested in the intersection between machine learning and robotics, where I aim to scale up reinforcement learning for downstream applications in real-world robot learning problems.

Email  /  Scholar  /  Twitter  /  Github  /  cv

We demonstrate the effectiveness of using quasimetric distance representations in horizon-generalization by performing multistep backups. This allows us to scale up compositional tasks to real-world, pixel-based tasks using offline GCRL.

Using a combination of Monte-Carlo contrastive learning and necessary invariances, we can find the optimal goal-reaching Q function with quasimetric representations in offline goal-conditioned reinforcement learning (GCRL).

We propose Temporal Representation Alignment (TRA), a policy learning method that utilizes the quasimetric property of temporal distances, and observe emergent capabilities in following compositional instructions when trained on a real world robot dataset.

We propose an effective and sample-efficient nonparametric adaptation method for learning new language-conditioned robotic manipulation tasks by searching for the best language decomposition and executing these instructions in inference.

Miscellaneous

I grew up in Orange County, California, so my collection of favorite sports teams are peculiar (Go Warriors, 49ers, Angels, and Ducks!). In my (somewhat) free time, I like to enjoy the following:

• Classical music (My favorite composers are Sergei Rachmaninoff, Richard Strauss, and Dmitri Shostakovich).
• Sports analytics. Thinking Basketball and Michael MacKelvie on YouTube are good introductions if you want to get to know more about NBA and NFL analytics.
• Playing Civilization (5 and 6).
• Weightlifting.
• Pedagogy.
• Cooking (mostly grilling).

Website template used from Jon Barron.