Motivation

Updateless Decision Theory (UDT) is a decision theory meant to deal with a fundamental problem in the existing decision theories: dynamic inconsistency, IE, having conflicting desires over time. In behavioral economics, humans are often modeled as hyperbolic discounters, meaning that rewards further away in time are seen as proportionately less important (so getting $100 one week from now is as good as $200 two weeks from now). This is dynamically inconsistent because the relative value of rewards changes as they get closer or further away in time. (Getting $100 one year from now sounds much less desirable than getting $200 one year plus one week from now.) This model explains some human behaviors, such as snoozing alarms repeatedly.^[1]

The dynamic inconsistency inherent in hyperbolic discounting can be fixed by exponential discounting, amongst other possibilities. However, dynamic inconsistencies can still occur for other reasons. The two most common decision theories today, Causal Decision Theory (CDT) and Evidential Decision Theory (EDT), are both dynamically inconsistent about Counterfactual Mugging: they refuse Omega when faced with the problem, but if asked beforehand, would see the value of agreeing.^[2]^[3]

Getting this issue right is critical in building a safe artificial general intelligence, as such an AI must analyze its own behavior and that of a next generation that it may build. Dynamically inconsistent AI systems have an incentive to engage in self-modification, but such self-modification is inherently risky.

Updateless Decision Theory was invented by Wei Dai and first described in Towards a New Decision Theory.

See also

Timeless decision theory
Ambient decision theory
Counterfactual mugging
Decision theory
Functional Decision Theory
Embedded Agency

Content

UDT specifies that the optimal agent is the one with the best policy—the best mapping from observations to actions—as estimated by its prior beliefs. ("Best" here, as in other decision theories, means one that maximizes expected utility.)

This definition may seem trivial, but in contrast, CDT and EDT both choose the "best" action in the current moment, IE, according to the posterior beliefs.

For example, standard game theory (which uses CDT) says that following through on costly threats is irrational. For example, suppose Alice says that she will hunt down Bob and beat him up i...