Volume 16 · Number 1 ·
Pages 057–060
The Relationship of Future State Maximization and von Foerster’s Ethical Imperative Through the Lens of Empowerment
Christian Guckelsberger, Christoph Salge & Daniel Polani
Log in download the full text in PDF
Abstract
Open peer commentary on the article “Foresight Rather than Hindsight? Future State Maximization As a Computational Interpretation of Heinz von Foerster’s Ethical Imperative” by Hannes Hornischer, Simon Plakolb, Georg Jäger & Manfred Füllsack. Abstract: We formulate a critique of the Future State Maximization (FSX) umbrella term and its connection to von Foerster’s Ethical Imperative by considering the relationship between Empowerment and other principles that the target article relates under the same heading. We furthermore draw on the wide body of existing Empowerment research to substantiate but also contradict some of the claims made.
Handling Editor: Alexander Riegler
Citation
Guckelsberger C., Salge C. & Polani D. (2020) The relationship of future state maximization and von Foerster’s ethical imperative through the lens of empowerment. Constructivist Foundations 16(1): 057–060. https://constructivist.info/16/1/057
Export article citation data: Plain Text · BibTex · EndNote · Reference Manager (RIS)
References
Anthony T., Polani D. & Nehaniv C. L. (2014) General self-motivation and strategy identification: Case studies based on Sokoban and Pac-Man. IEEE Transactions on Computational Intelligence and AI in Games 6(1): 1–17. ▸︎ Google︎ Scholar
Braitenberg V. (1986) Vehicles: Experiments in synthetic psychology. MIT Press, Cambridge MA. ▸︎ Google︎ Scholar
Cover T. M. & Thomas J. A. (2006) Elements of information theory. Second edition. Wiley-Interscience, Hoboken NJ. Originally published in 1999. ▸︎ Google︎ Scholar
Dewar R. C. (2003) Information theory explanation of the fluctuation theorem, maximum entropy production and self-organized criticality in non-equilibrium stationary states. Journal of Physics A: Mathematical and General 36(3): 631–641. ▸︎ Google︎ Scholar
Dewar R. C. (2005) Maximum entropy production and the fluctuation theorem. Journal of Physics A: Mathematical and General 38(21): 371–381. ▸︎ Google︎ Scholar
Di Paolo E. (2005) Autopoiesis, adaptivity, teleology, agency. Phenomenology and the Cognitive Sciences 4(4): 429–452. https://cepa.info/2269
Froese T. & Ziemke T. (2009) Enactive artificial intelligence: Investigating the systemic organization of life and mind. Artificial Intelligence 173(3–4): 466–500. https://cepa.info/279
Gregor K., Rezende D. J. & Wierstra D. (2017) Variational intrinsic control. In: Proceedings of the International Conference on Learning Representations (ICLR 2017) https://openreview.net/forum?id=Skc-Fo4Yg
Grinstein G. & Linsker R. (2007) Comments on a derivation and application of the “maximum entropy production” principle. Journal of Physics A: Mathematical and Theoretical 40(31): 9717–9720. ▸︎ Google︎ Scholar
Guckelsberger C. & Polani D. (2014) Effects of anticipation in individually motivated behaviour on survival and control in a multi-agent scenario with resource constraints. Entropy 16(6): 3357–3378. ▸︎ Google︎ Scholar
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 International Conference on the Synthesis and Simulation of Living Systems (ALIFE 2016) MIT Press, Cambridge MA: 704–711. https://cepa.info/4347
Guckelsberger C. (2020) Intrinsic motivation in computational creativity applied to videogames. PhD Thesis. Queen Mary, University of London. ▸︎ Google︎ Scholar
Guckelsberger C., Salge C. & Colton S. (2016) Intrinsically motivated general companion NPCs via coupled Empowerment maximisation. In: Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG 2016) IEEE Press, Piscataway NJ: 1–8. ▸︎ Google︎ Scholar
Klyubin A. S., Polani D. & Nehaniv C. L. (2005) Empowerment: A universal agent-centric measure of control. In: IEEE Congress on Evolutionary Computation, Volume 1. IEEE Press, Piscataway NJ: 128–135. ▸︎ Google︎ Scholar
Mohamed S. & Rezende D. J. (2015) Variational information maximisation for intrinsically motivated reinforcement learning. In: Cortes C., Lawrence N. D., Lee D. D., Sugiyama M. & Garnett R. (eds.) Proceedings of the Conference on Neural Information Processing Systems (NIPS 2015) MIT Press, Cambridge MA: 2125–2133. ▸︎ Google︎ Scholar
Perunov N., Marsland R. A. & England J. L. (2016) Statistical physics of adaptation. Physical Review X 6(2): 021036. ▸︎ Google︎ Scholar
Polani D. (2009) Information: Currency of life? HFSP Journal 3(5): 307–316. ▸︎ Google︎ Scholar
Salge C. & Polani D. (2017) Empowerment as replacement for the three laws of robotics. Frontiers in Robotics and AI 4: 16. ▸︎ Google︎ Scholar
Salge C., Glackin C. & Polani D. (2014) Changing the environment based on Empowerment as intrinsic motivation. Entropy 16(5): 2789–2819. ▸︎ Google︎ Scholar
Salge C., Glackin C. & Polani D. (2014) Empowerment – An introduction. In: Prokopenko M. (ed.) Guided self-organization: Inception. Springer, Berlin: 67–114. ▸︎ Google︎ Scholar
Shannon C. E. (1948) A mathematical theory of communication. Bell System Technical Journal 27(3): 379–423. ▸︎ Google︎ Scholar
Touchette H. & Lloyd S. (2000) Information-theoretic limits of control. Physical Review Letters 84(6–7): 1156–1159. ▸︎ Google︎ Scholar
Touchette H. & Lloyd S. (2004) Information-theoretic approach to the study of control systems. Physica A: Statistical Mechanics and its Applications 331(1–2): 140–172. ▸︎ Google︎ Scholar
Varela F. J. (1979) Principles of biological autonomy. Elsevier North-Holland, New York. ▸︎ Google︎ Scholar
Wissner-Gross A. D. & Freer C. E. (2013) Causal entropic forces. Physical Review Letters 110(16): 168702. ▸︎ Google︎ Scholar
Comments: 0
To stay informed about comments to this publication and post comments yourself, please log in first.