Formalizing Two Problems of Realistic World-Models

19 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Research Priorities for Robust and Beneficial Artificial Intelligence (2015, background): “This type of subgoal could lead to undesired consequences, and a better understanding of the conditions under which resource acquisition or radical stabilization is an optimal strategy (or likely to be selected by a given system) would be useful in mitigating its eﬀects.”
Questions of Reasoning Under Logical Uncertainty (2015, unknown): “0000029944.99888.a7.”