Towards autonomous artificial agents with an active self: modeling sense of control in situated action

Kahl S, Wiese S, Russwinkel N, Kopp S (2021)
Cognitive Systems Research 72: 50-62.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Kahl, SebastianUniBi ; Wiese, Sebastian; Russwinkel, Nele; Kopp, StefanUniBi
Abstract / Bemerkung
In this paper we present a computational modeling account of an active self in artificial agents. In particular we focus on how an agent can be equipped with a sense of control and how it arises in autonomous situated action and, in turn, influences action control. We argue that this requires laying out an embodied cognitive model that combines bottom-up processes (sensorimotor learning and fine-grained adaptation of control) with top-down processes (cognitive processes for strategy selection and decision-making). We present such a conceptual computational architecture based on principles of predictive processing and free energy minimization. Using this general model, we describe how a sense of control can form across the levels of a control hierarchy and how this can support action control in an unpredictable environment. We present an implementation of this model as well as first evaluations in a simulated task scenario, in which an autonomous agent has to cope with un-/predictable situations and experiences corresponding sense of control. We explore different model parameter settings that lead to different ways of combining low-level and high-level action control. The results show the importance of appropriately weighting information in situations where the need for low/high-level action control varies and they demonstrate how the sense of control can facilitate this.
Erscheinungsjahr
2021
Zeitschriftentitel
Cognitive Systems Research
Band
72
Seite(n)
50-62
eISSN
1610-1987
Page URI
https://pub.uni-bielefeld.de/record/2944539

Zitieren

Kahl S, Wiese S, Russwinkel N, Kopp S. Towards autonomous artificial agents with an active self: modeling sense of control in situated action. Cognitive Systems Research. 2021;72:50-62.
Kahl, S., Wiese, S., Russwinkel, N., & Kopp, S. (2021). Towards autonomous artificial agents with an active self: modeling sense of control in situated action. Cognitive Systems Research, 72, 50-62. https://doi.org/10.1016/j.cogsys.2021.11.005
Kahl, Sebastian, Wiese, Sebastian, Russwinkel, Nele, and Kopp, Stefan. 2021. “Towards autonomous artificial agents with an active self: modeling sense of control in situated action”. Cognitive Systems Research 72: 50-62.
Kahl, S., Wiese, S., Russwinkel, N., and Kopp, S. (2021). Towards autonomous artificial agents with an active self: modeling sense of control in situated action. Cognitive Systems Research 72, 50-62.
Kahl, S., et al., 2021. Towards autonomous artificial agents with an active self: modeling sense of control in situated action. Cognitive Systems Research, 72, p 50-62.
S. Kahl, et al., “Towards autonomous artificial agents with an active self: modeling sense of control in situated action”, Cognitive Systems Research, vol. 72, 2021, pp. 50-62.
Kahl, S., Wiese, S., Russwinkel, N., Kopp, S.: Towards autonomous artificial agents with an active self: modeling sense of control in situated action. Cognitive Systems Research. 72, 50-62 (2021).
Kahl, Sebastian, Wiese, Sebastian, Russwinkel, Nele, and Kopp, Stefan. “Towards autonomous artificial agents with an active self: modeling sense of control in situated action”. Cognitive Systems Research 72 (2021): 50-62.
Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®
Suchen in

Google Scholar