Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Mild Optimization
Tag
Relevant
New
Old
AISC project: SatisfIA – AI that satisfies without overdoing it
Jobst Heitzig
11 Nov 2023 18:22 UTC
11
points
0
comments
1
min read
LW
link
(docs.google.com)
Aspiration-based Q-Learning
Clément Dumas
and
Jobst Heitzig
27 Oct 2023 14:42 UTC
37
points
5
comments
11
min read
LW
link
AISC team report: Soft-optimization, Bayes and Goodhart
Simon Fischer
,
benjaminko
,
jazcarretao
,
DFNaiff
and
Jeremy Gillen
27 Jun 2023 6:05 UTC
37
points
2
comments
15
min read
LW
link
Requirements for a STEM-capable AGI Value Learner (my Case for Less Doom)
RogerDearnaley
25 May 2023 9:26 UTC
32
points
3
comments
15
min read
LW
link
[Question]
Why don’t quantilizers also cut off the upper end of the distribution?
Alex_Altair
15 May 2023 1:40 UTC
25
points
2
comments
1
min read
LW
link
Thinking about maximization and corrigibility
James Payor
21 Apr 2023 21:22 UTC
63
points
4
comments
5
min read
LW
link
Breaking the Optimizer’s Curse, and Consequences for Existential Risks and Value Learning
Roger Dearnaley
21 Feb 2023 9:05 UTC
10
points
1
comment
23
min read
LW
link
Validator models: A simple approach to detecting goodharting
beren
20 Feb 2023 21:32 UTC
14
points
1
comment
4
min read
LW
link
Reward is not Necessary: How to Create a Compositional Self-Preserving Agent for Life-Long Learning
Roman Leventov
12 Jan 2023 16:43 UTC
17
points
2
comments
2
min read
LW
link
(arxiv.org)
Soft optimization makes the value target bigger
Jeremy Gillen
2 Jan 2023 16:06 UTC
117
points
20
comments
12
min read
LW
link
Exploring Mild Behaviour in Embedded Agents
Megan Kinniment
27 Jun 2022 18:56 UTC
21
points
4
comments
18
min read
LW
link
Steam
abramdemski
20 Jun 2022 17:38 UTC
134
points
13
comments
5
min read
LW
link
1
review
When to use quantilization
RyanCarey
5 Feb 2019 17:17 UTC
65
points
5
comments
4
min read
LW
link
Optimization Regularization through Time Penalty
Linda Linsefors
1 Jan 2019 13:05 UTC
11
points
4
comments
3
min read
LW
link
Stable Pointers to Value III: Recursive Quantilization
abramdemski
21 Jul 2018 8:06 UTC
20
points
4
comments
4
min read
LW
link
Quantilal control for finite MDPs
Vanessa Kosoy
12 Apr 2018 9:21 UTC
14
points
0
comments
13
min read
LW
link
Thoughts on Quantilizers
Stuart_Armstrong
2 Jun 2017 16:24 UTC
2
points
0
comments
2
min read
LW
link
Quantilizers maximize expected utility subject to a conservative cost constraint
jessicata
28 Sep 2015 2:17 UTC
33
points
3
comments
5
min read
LW
link
Satisficers want to become maximisers
Stuart_Armstrong
21 Oct 2011 16:27 UTC
37
points
70
comments
1
min read
LW
link
The Optimizer’s Curse and How to Beat It
lukeprog
16 Sep 2011 2:46 UTC
97
points
84
comments
3
min read
LW
link