English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Acquiring Target Stacking Skills by Goal-Parameterized Deep Reinforcement Learning

Li, W., Bohg, J., & Fritz, M. (2017). Acquiring Target Stacking Skills by Goal-Parameterized Deep Reinforcement Learning. Retrieved from http://arxiv.org/abs/1711.00267.

Item is

Files

show Files
hide Files
:
arXiv:1711.00267.pdf (Preprint), 445KB
Name:
arXiv:1711.00267.pdf
Description:
File downloaded from arXiv at 2018-02-01 09:45
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Li, Wenbin1, Author           
Bohg, Jeannette2, Author
Fritz, Mario1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: Computer Science, Robotics, cs.RO,Computer Science, Artificial Intelligence, cs.AI,Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG
 Abstract: Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through interaction with the environment. We created a synthetic block stacking environment with physics simulation in which the agent can learn a policy end-to-end through trial and error. Thereby, we bypass to explicitly model physical knowledge within the policy. We are specifically interested in tasks that require the agent to reach a given goal state that may be different for every new trial. To this end, we propose a deep reinforcement learning framework that learns policies which are parametrized by a goal. We validated the model on a toy example navigating in a grid world with different target positions and in a block stacking task with different target structures of the final tower. In contrast to prior work, our policies show better generalization across different goals.

Details

show
hide
Language(s): eng - English
 Dates: 2017-11-012017-11-222017
 Publication Status: Published online
 Pages: 10 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1711.00267
URI: http://arxiv.org/abs/1711.00267
BibTex Citekey: Li1711.00267
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show