Learning complex goals with iterated amplification

OpenAI Blog · 7 years ago

Researchers proposed iterated amplification, an AI safety technique that breaks down complex tasks into simpler subtasks rather than relying on labeled data or reward functions to train AI systems. The approach has only been tested on toy algorithmic problems so far, with no concrete benchmarks or performance metrics published. If successful at scale, the method could address the challenge of specifying AI behavior for goals too complicated for humans to directly specify.