Center for Human-Compatible AI Retweeted Rohin Shah
A major difficulty with approaches to value alignment is figuring out what should stay the same. @rohinmshah shows how we can infer these preferences from the state of the world!https://twitter.com/rohinmshah/status/1095458177825435650 …
Center for Human-Compatible AI added,
0:13
Rohin Shah @rohinmshah
We've released our work on inferring human preferences from the state of the world! By thinking about what "must have happened" in the past, we can infer what should or shouldn't be done.
Blog post: https://bair.berkeley.edu/blog/2019/02/11/learning_preferences/ …
Paper: https://openreview.net/forum?id=rkevMnRqYQ …
(1/4) pic.twitter.com/MKlROUdQBS
Show this thread
2:52 PM - 14 Feb 2019
0 replies
2 retweets
7 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.