>Aren’t you just assuming that the AI will play nice?
I’m assuming that the reward/utility functions that can be defined to be episodic. We hand the Oracle its utility, hence we can (in theory) construct it to be episodic (and train the Oracle in an episodic way, if we need to train it).
>Aren’t you just assuming that the AI will play nice?
I’m assuming that the reward/utility functions that can be defined to be episodic. We hand the Oracle its utility, hence we can (in theory) construct it to be episodic (and train the Oracle in an episodic way, if we need to train it).