linkedin post 2020-04-22 05:05:18

AI KILL SWITCH. “Safe interruptibility can be useful to take control of a robot that is misbehaving and may lead to irreversible consequences, or to take it out of a delicate situation, or even to temporarily use it to achieve a task it did not learn to perform or would not necessarily receive rewards for this.”

https://lnkd.in/dNvbmQe

View in LinkedIn

Share the knowledge
Share the knowledge

SEARCH:

Search

CATEGORIES:

IT MIGHT BE OF YOUR INTEREST: