Homer Walke

Hello! I'm a student at Brown studying computer science. I work in the Robotics Group with Professor Michael Littman and in the Visual Computing Group with Professor Daniel Ritchie.

Email  /  Github

profile photo
Learning to Infer Shape Programs Using Latent Execution Self Training
Homer Walke, R. Kenny Jones, Daniel Ritchie
arXiv, 2020

We designed a new method for shape program inference based on self-training that works with black box program executors. We demonstrate that it converges faster and achieves better reconstruction quality than policy gradient reinforcement learning.

DeepLTLf: Learning Linear Temporal Logic Specifications with a Specialized Neural Operator
Homer Walke, Daniel Ritter, Carl Trimbach Michael Littman

We developed an approach for synthesizing LTL formulas from demonstrations using deep networks outfitted with a custom neural operator. We show that our method learns LTL formulas that capture extended sequences of actions, scaling better than SAT-based approaches.