Dynamic consistency and decision making under vacuous belief
This work addresses foundational issues in AI decision-making under uncertainty, but it appears incremental as it builds on existing theories without introducing a new paradigm.
The paper tackles the problem of ensuring dynamic consistency in artificial agents under ignorance by combining economic decision-making theories with computer science uncertainty representations, resulting in a formal condition for sequential consistency in certainty equivalence operators for Nehring-Puppe preferences.
The ideas about decision making under ignorance in economics are combined with the ideas about uncertainty representation in computer science. The combination sheds new light on the question of how artificial agents can act in a dynamically consistent manner. The notion of sequential consistency is formalized by adapting the law of iterated expectation for plausibility measures. The necessary and sufficient condition for a certainty equivalence operator for Nehring-Puppe's preference to be sequentially consistent is given. This result sheds light on the models of decision making under uncertainty.