Learning Control for Air Hockey Striking Using Deep Reinforcement Learning

Ayal Taitler, Nahum Shimkin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

We consider the task of learning control policies for a robotic mechanism striking a puck in an air hockey game. The control signal is a direct command to the robot's motors. We employ a model free deep reinforcement learning framework to learn the motoric skills of striking the puck accurately in order to score. We propose certain improvements to the standard learning scheme which make the deep Q-learning algorithm feasible when it might otherwise fail. Our improvements include integrating prior knowledge into the learning scheme, and accounting for the changing distribution of samples in the experience replay buffer. Finally we present our simulation results for aimed striking which demonstrate the successful learning of this task, and the improvement in algorithm stability due to the proposed modifications.

Original languageEnglish
Title of host publicationProceedings - 2017 International Conference on Control, Artificial Intelligence, Robotics and Optimization, ICCAIRO 2017
PublisherInstitute of Electrical and Electronics Engineers
Pages22-27
Number of pages6
ISBN (Electronic)9781509065363
DOIs
StatePublished - 1 Jul 2017
Externally publishedYes
Event2017 International Conference on Control, Artificial Intelligence, Robotics and Optimization, ICCAIRO 2017 - Prague, Czech Republic
Duration: 20 May 201722 May 2017

Publication series

NameProceedings - 2017 International Conference on Control, Artificial Intelligence, Robotics and Optimization, ICCAIRO 2017
Volume2018-January

Conference

Conference2017 International Conference on Control, Artificial Intelligence, Robotics and Optimization, ICCAIRO 2017
Country/TerritoryCzech Republic
CityPrague
Period20/05/1722/05/17

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Learning Control for Air Hockey Striking Using Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this