A narrative history of the problem of getting machine-learning systems to do what we intend, connecting fairness, reinforcement learning, imitation and inverse reinforcement learning through interviews with researchers.
This is an external publication. AI Governance LK did not write it; the summary and notes on this page are our own.
Why it matters
Particularly good for readers coming from law, policy or the humanities, because it shows how today’s technical debates grew out of concrete problems with deployed systems.
What you will learn
- Connect fairness research and alignment research
- Explain learning from demonstration and preferences
Before you start
Suggested background. This is editorial guidance, not a requirement.
- None
How to cite
Christian, B. (2020). The Alignment Problem: Machine Learning and Human Values. W. W. Norton & Company.