Updateless decision theory
Updateless Decision Theory (UDT) is a new decision theory meant to deal with a fundamental problem in the existing decision theories: Treating the agent as a part of the world. In contrast, the most common decision theory today, Causal Decision Theory (CDT), the decision is not part of the world model--it is the output of the CDT, but in the context of the world the agent's decision is "magic": It is uncaused, like a dualist version of a soul with free will.
Getting this issue right is critical in building a self-improving artificial general intelligence. Such an AI must analyze its own behavior and that of a next generation that it may build.
UDT specifies that the optimal agent is the one with the best algorithm--the best mapping from observations to actions--across a probability distribution of all world-histories. ("Best" here, as in other decision theories, means one that maximizes a utility/reward function.)
This definition may seem trivial, but in contrast, CDT says that an agent should choose the best option at any given moment based on the effects of that action.
- indexical uncertainty and the Axiom of Independence by Wei Dai
- Towards a New Decision Theory by Wei Dai
- Anthropic Reasoning in UDT by Wei Dai
- The Absent-Minded Driver by Wei Dai
- Why (and why not) Bayesian Updating? by Wei Dai
- What Are Probabilities, Anyway? by Wei Dai
- Explicit Optimization of Global Strategy (Fixing a Bug in UDT1) by Wei Dai
- List of Problems That Motivated UDT by Wei Dai
- Another attempt to explain UDT by cousin_it
- All posts tagged "UDT"
In addition to whole posts on UDT, there are also a number of comments which contain important information, often on less relevant posts.
Problem Class Dominance in Predictive Dilemmas, section 3.4. (The best summary to date.)
- An introduction to decision theory (series of posts)