All Else Being Equal Be Empowered | SpringerLink
The classical approach to using utility functions suffers from the drawback of having to design and tweak the functions on a case by case basis. Inspired by examples from the animal kingdom, social sciences and games we propose empowerment, a rather universal function, defined as the information-theoretic capacity of an agent’s actuation channel. The concept applies to any sensorimotoric apparatus. Empowerment as a measure reflects the properties of the apparatus as long as they are observable due to the coupling of sensors and actuators via the environment. Access provided by University of Chicago. Download to read the full chapter text Ashby, W.R.: An Introduction to Cybernetics. Chapman & Hall Ltd., Boca Raton (1956) MATH Google Scholar Gibson, J.J.: The Ecological Approach to Visual Perception. Houghton Mifflin Company, Boston (1979) Google Scholar Shannon, C.E.: A mathematical theory of communication. The Bell System Technical Journal 27, 379–423 (1948) MATH MathSciNet Googl
Abstract The classical approach to using utility functions suffers from the drawback of having to design and tweak the functions on a case by case basis. Inspired by examples from the animal kingdom, social sciences and games we propose empowerment , a rather universal function, defined as the information-theoretic capacity of an agent’s actuation channel. The concept applies to any sensorimotoric apparatus. Empowerment as a measure reflects the properties of the apparatus as long as they are observable due to the coupling of sensors and actuators via the environment. This is a preview of subs
Explore this link on the map →related reading
- Plasticity as the Mirror of Empowerment (David Abel) - Sensorimotor AI Journal Clubsensorimotorai.github.io
- A Crash Course in the Neuroscience of Human Motivation — LessWronglesswrong.com
- When Models Manipulate Manifolds: The Geometry of a Counting Tasktransformer-circuits.pub
- Augmenting Human Intellect: A Conceptual Framework - 1962 (AUGMENT,3906,) - Doug Engelbart Institutedougengelbart.org
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- Arjun Virkarjunvirk.com
- Utility Maximization = Description Length Minimization — LessWronglesswrong.com
- Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com
- [1912.01683] Optimal Policies Tend to Seek Powerarxiv.org
- [1605.03142] Self-Modification of Policy and Utility Function in Rational Agentsarxiv.org
- Bengt Holmström - Prize Lecture_ Pay for Performance and Beyond.pdfeconomics.mit.edu
- Reward Function Design: a starter pack — LessWronglesswrong.com