All of fwang's Comments + Replies

Happens all the time in decision theory & reinforcement learning: the average of many good plans is often a bad plan, and a bad plan followed to the end is often both more rewarding & informative than switching at every timestep between many good plans. Any kind of multi-modality or need for extended plans (eg due to upfront costs/investments) will do it, and exploration is quite difficult - just taking the argmax or adding some randomness to action choices is not nearly enough, you need "deep exploration" (as Osband likes to call it) to follow a s

... (read more)

Honesty is the best policy. <3 Mom

Regarding the assumptions for a strong AI that will cease cooperating and pursue its own values, the scenario presented assumed that 1) L will have the ability to subvert S's control, and then 4a) S must be unaware that L has that ability. That is (if I understand this correctly), the ability for L to subvert S is undetected. But if it's the case that we assume 1), then perhaps S should instead operate under the assumption that L already has the ability (and perhaps even knowledge) to subvert, but S doesn't know what ex... (read more)

This may be a little basic, but if you're already going with the "efficient at transmitting forces" idea for physical posture, then I think a good analogy in terms of mental posture would simply be "efficient at processing information" (of which being rational is a pretty useful method, just like keeping your spine, er, non-kyphotic is useful).

This is much more concise than:

how efficiently one's patterns of directing attention let one mentally navigate one's environment

while at the same time relatively neutral with respect to the ac... (read more)