Search Results for author:
Found 5 papers, 2 papers with code
PushWorld: A benchmark for manipulation planning with tools and movable obstacles
We provide a benchmark of more than 200 PushWorld puzzles in PDDL and in an OpenAI Gym environment.
Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
The recent adaptation of deep neural network-based methods to reinforcement learning and planning domains has yielded remarkable progress on individual tasks.
Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data
We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer training images than required for competing discriminative methods.
GRED: Graph-Regularized 3D Shape Reconstruction from Highly Anisotropic and Noisy Images
Analysis of microscopy images can provide insight into many biological processes.
Structured Learning for Cell Tracking
We study the problem of learning to track a large quantity of homogeneous objects such as cell tracking in cell culture study and developmental biology.
