Problem Class Dominance in Predictive Dilemmas

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): “Example research topics in this area include reasoning and decision under bounded computational resources à la Horvitz and Russell (Horvitz 1987; Russell and Subramanian 1995), how to take into account correlations between AI systems’ behaviors and those of their environments or of other agents (Ten”
Aligning Superintelligence with Human Interests: A Technical Research Agenda (2015, background): “For example, Wei Dai’s “updateless decision theory” (UDT) is a new take on decision theory that systematically outperforms causal decision theory (Hintze 2014), and two of the insights behind UDT highlight a number of tractable open problems (Soares and Fallenstein 2014).”
Agent Foundations for Aligning Machine Intelligence with Human Interests: A Technical Research Agenda (2017, background): “Many existing tools for studying reasoning, such as game theory, standard probability theory, and Bayesian networks, all assume that reasoners are logically omniscient.”
Functional Decision Theory: A New Theory of Instrumental Rationality (2017, unknown): “are smart enough to know what they would do upon arriving in the city, this means that neither can honestly claim that they would pay. The driver, detecting the lie, leaves them in the desert to die (Hintze 2014). The prescriptions of CDT and EDT here run contrary to many people’s intuitions, which ”