Search Results for author:
Found 4 papers, 1 papers with code
Learning Control by Iterative Inversion
The key challenge is a $\textit{distribution shift}$ between the desired outputs and the outputs of an initial random guess, and we prove that iterative inversion can steer the learning correctly, under rather strict conditions on the function.
Validate on Sim, Detect on Real -- Model Selection for Domain Randomization
We show that our score - VSDR - can significantly improve the accuracy of policy ranking without requiring additional real world data.
Efficient Self-Supervised Data Collection for Offline Robot Learning
In this work, we propose that data collection policies should actively explore the environment to collect diverse data.
Neural Network Distiller: A Python Package For DNN Compression Research
This paper presents the philosophy, design and feature-set of Neural Network Distiller, an open-source Python package for DNN compression research.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
