List of technical AI alignment agendas
From Issawiki (static archive)
This is a list of technical AI alignment agendas.
- Iterated amplification
- Embedded agency
- Comprehensive AI services
- Ambitious value learning
- Factored cognition
- Recursive reward modeling
- Debate
- Interpretability
- Inverse reinforcement learning
- Preference learning
- Cooperative inverse reinforcement learning
- Imitation learning
- Alignment for advanced machine learning systems
- Learning-theoretic AI alignment
- Counterfactual reasoning
Categories: