Summer 2019

Aligning ML objectives with human values

Monday, Aug. 5, 2019 2:15 pm3:00 pm PDT

Add to Calendar


Paul Christiano (Open AI)

For open-ended tasks it is often difficult to measure or even define performance. For example, it's unclear what objective I should optimize in order to better understand how I should spend my time or which laws we should pass. I'll describe this problem in the language of learning theory, lay out the approaches that seem most promising to me, and overview some current work.