
53 - Mimi Liljeholm: The Neuroscience of Agency, Learning, and How It Helps Us Understand AI
Stanford Psychology Podcast
00:00
Planning for Changes in Outcome Values
We always want to be in a situation where, you know, we're kind of planning for those changes and preferences. And the best way to do that is to be in an environment where you can really control the outcomes usinging actions. I don't have to plan for every possible outcome value; i will just choose environments with instrumental divergence. That makes up one way. But another alternative is that you about how valuable some place is that you're going to and then youPlan for every possible change in outcome value. How much would i like that place if i like water when i get there? How much wouldi like it if i hate water when i getting there? Eh? It's
Transcript
Play full episode