Influence-Based Abstraction in Deep Reinforcement Learning

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

56 Downloads (Pure)


thousands, or even millions of state variables. Unfortunately, applying reinforcement learning algorithms to handle complex tasks becomes more and more challenging as the number of state variables increases. In this paper, we build on the concept of influence-based abstraction which tries to tackle such scalability issues by decomposing large systems into small regions. We explore this method in the context of deep reinforcement learning, showing that by keeping track of a small set of variables in the history of previous actions and observations we can learn policies that can effectively control a local region in the global system.
Original languageEnglish
Title of host publicationAAMAS Workshop on Adaptive Learning Agents (ALA)
Place of PublicationMontreal, Canada
Number of pages8
Publication statusPublished - 13 May 2019
EventALA 2019 - Workshop at AAMAS 2019 - Montreal, Canada
Duration: 13 May 201914 May 2019


WorkshopALA 2019 - Workshop at AAMAS 2019

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.


  • Reinforcement Learning
  • Dec-POMDP
  • Influence-based abstraction


Dive into the research topics of 'Influence-Based Abstraction in Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this