Incorporating Sense of Control in Dynamic Multi-Tasking Problems: A Model-based Hierarchical Reinforcement Learning Approach

Österdiekhoff A (Accepted)
Doctoral Consortium.

Kurzbeitrag Konferenz / Poster | Angenommen | Englisch
 
Download
OA 462.50 KB
Abstract / Bemerkung
Autonomous intelligent agents often fail in complex dynamic multi-tasking scenarios that are easily solvable for humans. For example, agents fail to adapt to new situations or cannot coordinate task switching between multiple tasks. A reason for this inability could be that in comparison to humans intelligent agents are missing cognitive capabilities. For one thing, humans have a sense of control (SoC), the feeling of being in control for successfully solving tasks. In general, it is unclear how to model the SoC of humans and how to make use of it for autonomous intelligent agents. This paper will present an approach to model the SoC and incorporating into autonomous intelligent agents modeled by model-based hierarchical reinforcement learning. Moreover, planned studies on the SoC in humans in multi-tasking problem scenarios are discussed. The hypothesis is that using this approach and equipping autonomous intelligent agents with a SoC will lead to improved decision-making in complex dynamic multi-tasking problems.
Erscheinungsjahr
2023
Serien- oder Zeitschriftentitel
Doctoral Consortium
Konferenz
15th International Conference on Agents and Artificial Intelligence - Doctoral Consortium (ICAART)
Konferenzort
Lissabon
Konferenzdatum
2023-02-22 – 2023-02-24
Page URI
https://pub.uni-bielefeld.de/record/2969471

Zitieren

Österdiekhoff A. Incorporating Sense of Control in Dynamic Multi-Tasking Problems: A Model-based Hierarchical Reinforcement Learning Approach. Doctoral Consortium. Accepted.
Österdiekhoff, A. (Accepted). Incorporating Sense of Control in Dynamic Multi-Tasking Problems: A Model-based Hierarchical Reinforcement Learning Approach. Doctoral Consortium. https://doi.org/10.13140/RG.2.2.15135.57766
Österdiekhoff, Annika. Accepted. “Incorporating Sense of Control in Dynamic Multi-Tasking Problems: A Model-based Hierarchical Reinforcement Learning Approach”, Doctoral Consortium, .
Österdiekhoff, A. (Accepted). Incorporating Sense of Control in Dynamic Multi-Tasking Problems: A Model-based Hierarchical Reinforcement Learning Approach. Doctoral Consortium.
Österdiekhoff, A., Accepted. Incorporating Sense of Control in Dynamic Multi-Tasking Problems: A Model-based Hierarchical Reinforcement Learning Approach. Doctoral Consortium.
A. Österdiekhoff, “Incorporating Sense of Control in Dynamic Multi-Tasking Problems: A Model-based Hierarchical Reinforcement Learning Approach”, Doctoral Consortium, Accepted.
Österdiekhoff, A.: Incorporating Sense of Control in Dynamic Multi-Tasking Problems: A Model-based Hierarchical Reinforcement Learning Approach. Doctoral Consortium. (Accepted).
Österdiekhoff, Annika. “Incorporating Sense of Control in Dynamic Multi-Tasking Problems: A Model-based Hierarchical Reinforcement Learning Approach”. Doctoral Consortium (Accepted).
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2024-05-02T15:53:49Z
MD5 Prüfsumme
db17716b5f7f98966b440fa8cc5d3e14


Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar