An AGI with Time-Inconsistent Preferences

📖 Description

An AGI with Time -Inconsistent Preferences May 28, 2019 James D. Miller and Roman Yampolskiy [email removed] , roman.yampolskiy@louisville. edu Introduction This paper reveals a trap for artificial general intelligence (AGI) theorists who use economists? standard method of discounting. This trap is implicitly and falsely assuming that a rational AGI would have time - consistent preferences. An agent with time -inconsistent preferences knows that its future self will disagree with its current se lf concerning intertemporal decision making . Such an agent cannot automatically trust its future self to carry out plans that its current self considers optimal. Economists have long used utility functions to model how rational agents behave (see Mas -Colell et al. , 1995) . AGI theorists often rely on these utility function s because they assume that an AGI would either start out as rational or modify itself to become rational (see Omohun...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/1906.10536