We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into simpler sub-tasks, rather than by providing labeled data or a reward function. Although this idea is in its very
RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.
This simulated
RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.
This simulated
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
