Zero-Shot Visual Imitation

From statwiki
Revision as of 21:03, 30 October 2018 by Vrajendr (talk | contribs)
Jump to navigation Jump to search
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

This page contains a summary of the paper "Zero-Shot Visual Imitation" by Pathak, D., Mahmoudieh, P., Luo, G., Agrawal, P. et al. It was published at the International Conference on Learning Representations (ICLR) in 2018.

Introduction

Learning to Imitate Without Expert Supervision

Learning the Goal-Conditioned Skill Policy (GSP)

Forward Consistency Loss

Goal Recognizer

Ablations and Baselines

Experiments

Rope Manipulation

Navigation in Indoor Office Environments

3D Navigation in VizDoom

Related Work

Discussion

Critique