One-Shot Imitation Learning

From statwiki
Revision as of 04:22, 21 February 2018 by Isucholu (talk | contribs) (Skeleton)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Introduction

Related Work

One-Shot Imitation Learning

Problem Formalization

Block Stacking Tasks

Algorithm

Architecture

Demonstration Network

Temporal Dropout:

Neighborhood Attention:

Context network

Attention over demonstration:

Attention over current state:

Manipulation network

Experiments

Performance Evaluation

Visualization

Conclusions

Criticisms

References