RSS

Re­ward Functions

TagLast edit: 7 Dec 2021 3:22 UTC by [Error communicating with LW2 server]

Draft pa­pers for REALab and De­cou­pled Ap­proval on tampering

28 Oct 2020 16:01 UTC
47 points
2 comments1 min readLW link

Why we want un­bi­ased learn­ing processes

Stuart_Armstrong20 Feb 2018 14:48 UTC
13 points
3 comments3 min readLW link

$100/​$50 re­wards for good references

Stuart_Armstrong3 Dec 2021 16:55 UTC
18 points
3 comments1 min readLW link

Thoughts on re­ward en­g­ineer­ing

paulfchristiano24 Jan 2019 20:15 UTC
30 points
30 comments11 min readLW link

Re­ward func­tion learn­ing: the value function

Stuart_Armstrong24 Apr 2018 16:29 UTC
9 points
0 comments11 min readLW link

Re­ward func­tions and up­dat­ing as­sump­tions can hide a mul­ti­tude of sins

Stuart_Armstrong18 May 2020 15:18 UTC
16 points
2 comments9 min readLW link

Re­ward func­tion learn­ing: the learn­ing process

Stuart_Armstrong24 Apr 2018 12:56 UTC
6 points
11 comments8 min readLW link

Utility ver­sus Re­ward func­tion: par­tial equivalence

Stuart_Armstrong13 Apr 2018 14:58 UTC
9 points
5 comments5 min readLW link

In­tu­itive ex­am­ples of re­ward func­tion learn­ing?

Stuart_Armstrong6 Mar 2018 16:54 UTC
7 points
3 comments2 min readLW link

Prob­a­bil­ities, weights, sums: pretty much the same for re­ward functions

Stuart_Armstrong20 May 2020 15:19 UTC
11 points
1 comment2 min readLW link

The re­ward en­g­ineer­ing prob­lem

paulfchristiano16 Jan 2019 18:47 UTC
24 points
3 comments7 min readLW link
No comments.