Difference between revisions of "Zero-Shot Visual Imitation"

From statwiki
Jump to: navigation, search
Line 1: Line 1:
 
This page contains a summary of the paper "[https://openreview.net/pdf?id=BkisuzWRW 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.  
 
This page contains a summary of the paper "[https://openreview.net/pdf?id=BkisuzWRW 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=
+
==Introduction==
  
=Learning to Imitate Without Expert Supervision=
+
==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==

Revision as of 21:03, 30 October 2018

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