Domain adaptation for reinforcement learning on the Atari

Research output: Chapter in Book/Report/Conference proceedingConference publication

Abstract

Deep Reinforcement learning is a powerful machine learning paradigm that has had significant success across a wide range of control problems. This success often requires long training times to achieve. Observing that many problems share similarities, it is likely that much of the training done could be redundant if knowledge could be efficiently and appropriately shared across tasks. In this paper we demonstrate a novel adversarial domain adaptation approach to transfer state knowledge between domains and tasks on the Atari game suite. We show how this approach can successfully transfer across very different visual domains of the Atari platform. We focus on semantically related games that involve returning a ball with the user controlled agent. Our experiments demonstrate that our method reduces the number of samples required to successfully train an agent to play an Atari game.

Original languageEnglish
Title of host publication18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
PublisherACM
Pages1859-1861
Number of pages3
ISBN (Electronic)9781510892002
ISBN (Print)978-1-4503-6309-9
Publication statusPublished - 8 May 2019
Event18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019 - Montreal, Canada
Duration: 13 May 201917 May 2019

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume4
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Conference

Conference18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
CountryCanada
CityMontreal
Period13/05/1917/05/19

Bibliographical note

© 2019 International Foundation for Autonomous Agents and
Multiagent Systems (www.ifaamas.org).

Keywords

  • Deep learning
  • Domain adaptation
  • Reinforcement learning

Fingerprint Dive into the research topics of 'Domain adaptation for reinforcement learning on the Atari'. Together they form a unique fingerprint.

Cite this