OpenAI Blog · Dec 21, 2016
Faulty reward functions in the wild
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Faulty reward functions in the wild. Reinforcement learning algorithms can break in surprising, counterintuitive ways. In this post we’ll explore one failure mode, which is where you misspecify your reward function. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Faulty reward functions in the wild' affects your current setup before relying on it in production.
ai