this only works if we specified the goal and the cost correctly
Wait, why doesn’t it work if you just specify the cost (impact) correctly?
Suppose the goal dramatically overvalues some option; then the AI would be willing to pay large (correctly estimated) costs in order to achieve “even larger” (incorrectly estimated) gains.
Wait, why doesn’t it work if you just specify the cost (impact) correctly?
Suppose the goal dramatically overvalues some option; then the AI would be willing to pay large (correctly estimated) costs in order to achieve “even larger” (incorrectly estimated) gains.