• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Domain Shifts in Reinforcement Learning: Identifying Disturbances in Environments
 
  • Details
  • Full
Options
2021
Conference Paper
Titel

Domain Shifts in Reinforcement Learning: Identifying Disturbances in Environments

Abstract
A significant drawback of End-to-End Deep Reinforcement Learning (RL) systems is that they return an action no matter what situation they are confronted with. This is true even for situations that differ entirely from those an agent has been trained for. Although crucial in safety-critical applications, dealing with such situations is inherently difficult. Various approaches have been proposed in this direction, such as robustness, domain adaption, domain generalization, and out-of-distribution detection. In this work, we provide an overview of approaches towards the more general problem of dealing with disturbances to the environment of RL agents and show how they struggle to provide clear boundaries when mapped to safety-critical problems. To mitigate this, we propose to formalize the changes in the environment in terms of the Markov Decision Process (MDP), resulting in a more formal framework when dealing with such problems. We apply this framework to an example real-world scenario and show how it helps to isolate safety concerns.
Author(s)
Haider, Tom
Fraunhofer-Institut für Kognitive Systeme IKS
Schmoeller Roza, Felippe
Fraunhofer-Institut für Kognitive Systeme IKS
Eilers, Dirk
Fraunhofer-Institut für Kognitive Systeme IKS
Roscher, Karsten
Fraunhofer-Institut für Kognitive Systeme IKS
Günnemann, Stephan
Technische Univ. München, München
Hauptwerk
Workshop on Artificial Intelligence Safety, AISafety 2021. Proceedings. Online resource
Funder
Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und Energie StMWi
Konferenz
Workshop on Artificial Intelligence Safety (AISafety) 2021
International Joint Conference on Artificial Intelligence (IJCAI) 2021
File(s)
N-640441.pdf (3.17 MB)
Language
English
google-scholar
Fraunhofer-Institut für Kognitive Systeme IKS
Tags
  • reinforcement learnin...

  • RL

  • safety critical

  • Markov Decision Proce...

  • MDP

  • safety

  • Safe Intelligence

  • robustness

  • domain shift

  • out of distribution

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022