Publication 4347

Guckelsberger C. & Salge C. (2016) Does empowerment maximisation allow for enactive artificial agents. In: Gershenson C., Froese T., Siqueiros J. M., Aguilar W., Izqueirdo E. J. & Sayama H. (eds.) Proceedings of the Fifteenth International Conference on the Synthesis and Simulation of Living Systems (Alife 2016). MIT Press, Cambridge MA: 704–711. Fulltext at https://cepa.info/4347
The enactive AI framework wants to overcome the sense-making limitations of embodied AI by drawing on the bio-systemic foundations of enactive cognitive science. While embodied AI tries to ground meaning in sensorimotor interaction, enactive AI adds further requirements by grounding sensorimotor interaction in autonomous agency. At the core of this shift is the requirement for a truly intrinsic value function. We suggest that empowerment, an information-theoretic quantity based on an agents embodiment, represents such a function. We highlight the role of empowerment maximisation in satisfying the requirements of enactive AI, i.e. establishing constitutive autonomy and adaptivity, in detail. We then argue that empowerment, grounded in a precarious existence, allows an agent to enact a world based on the relevance of environmental features in respect to its own identity.

External

The publication has not yet bookmarked in any reading list

You cannot bookmark this publication into a reading list because you are not member of any
Log in to create one.

There are currently no annotations

To add an annotation you need to log in first

Download statistics

Log in to view the download statistics for this publication
Export bibliographic details as: CF Format · APA · BibTex · EndNote · Harvard · MLA · Nature · RIS · Science