For example, an RL agent that learns a policy that looks good to humans but isn't. Adversarial examples that only fool a neural nets wouldn't count.

New Answer
New Comment

1 Answers sorted by

For example, an RL agent that learns a policy that looks good to humans but isn't. Adversarial examples that only fool a neural nets wouldn't count.

[This comment is no longer endorsed by its author]
2 comments, sorted by Click to highlight new comments since: Today at 5:20 AM

Could you clarify this a bit? I assume you are thinking about subsets of specification gaming that would not be obvious if they were happening?

If so, then I guess all the adversarial examples in image classification comes to mind, which fits specification gaming pretty well and required quite a large literature to understand.

[-][anonymous]5y10

Thanks, updated.