x

LESSWRONG

LW

Joel_Saarinen — LessWrong

Joel_Saarinen

Joel_Saarinen

Message

Amsterdam-based AIS researcher and Logic MSc. student focused on reinforcement learning theory and value learning. More info on my site joelsaarinen.nl

46

1

2

3y

Joel_Saarinen

Amsterdam-based AIS researcher and Logic MSc. student focused on reinforcement learning theory and value learning. More info on my site joelsaarinen.nl

Value learning in the absence of ground truth

Epistemic Status: My best guess. Summary The problem of aligning AI is often phrased as the problem of aligning AI with human values, where “values” refers roughly to the normative considerations one leans upon in making decisions. Understood in this way, solving the problem would amount to first articulating the...

Feb 5, 2024•47