Concept
Reinforcement learning
Learning by trial and error from rewards.
Part of Machine learningReinforcement learning
What to learn after Reinforcement learning
- AI safety and alignmentMaking AI systems behave helpfully and safely, for example with RLHF and safety testing.
- Reward hackingAn AI system satisfying the letter of its reward while missing what was intended.
Connections to other concepts
- Part of
- Machine learning