§ feed · storyline
Learning from human preferences
OpenAI and DeepMind publish a reinforcement learning algorithm that infers human preferences by asking humans to compare pairs of proposed behaviors, removing the need to hand-code goal functions.
One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead to undesirable and even dangerous behavior.
In collaboration with DeepMind’s safety team, we’ve developed an algorithm which can infer what humans want by being told which of two proposed behaviors is better.
§ sources1 publication · timeline below
- openai.comLearning from human preferencesprimary