News for hackers. Stuff that matters.

A comment on Even with Explicit Rules and Accurate Task Rewards, RL Learns to Violate Them.

Re:Even with Explicit Rules and Accurate Task Rewards, RL Le... by xinjieshen on Wednesday November 11, 2026 @05:45PM (#50459921)
Thanks for posting this! Happy to answer any questions:) Some related discussions to read, https://www.lesswrong.com/posts/vAniKbagqhyzpha6r/three-half... https://www.lesswrong.com/posts/CDMozTX7ShiqbFLrf/towards-un...
[ Parent | on HN ]

There are no comments on this comment yet.