Patrick Yin

Hello! I am a fourth-year undergraduate studying computer science at UC Berkeley.

I currently do research with Prof. Sergey Levine at the Robotic AI and Learning Lab. I was previously a machine learning / computer vision intern at Ambi Robotics.

patrickhaoy @ berkeley.edu  /  Resume  /  Google Scholar  /  Github  /  LinkedIn

I'm broadly interested in building intelligent robots.

We propose Fine-Tuning with Lossy Affordance Planner (FLAP), a framework that leverages diverse offline data for learning representations, goal-conditioned policies, and affordance models that enable rapid fine-tuning to new tasks in target scenes.

We propose Planning to Practice (PTP), a method which makes it practical to train goal-conditioned policies for long-horizon tasks.

We propose a new form of state abstraction called goal-conditioned bisimulation that captures functional equivariance, allowing for the reuse of skills to achieve new goals in goal-conditioned reinforcement learning.

Worked on improving the computer vision system which powers AmbiSort.

Worked on the Insights Team, which tracks UiPath's entire robotic process automation program.