Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
16 posts
Utility Functions
Coherence Arguments
Orthogonality Thesis
Coherent Extrapolated Volition
Indexical Information
10 posts
Quantilization
Mild Optimization
47
Take 7: You should talk about "the human's utility function" less.
Charlie Steiner
12d
22
63
Three ways that "Sufficiently optimized agents appear coherent" can be false
Wei_Dai
3y
3
52
Buridan's ass in coordination games
jessicata
4y
26
69
The "Measuring Stick of Utility" Problem
johnswentworth
6mo
22
128
An Orthodox Case Against Utility Functions
abramdemski
2y
53
88
Coherence arguments imply a force for goal-directed behavior
KatjaGrace
1y
27
22
Conceptual problems with utility functions
Dacyn
4y
12
101
Coherence arguments do not entail goal-directed behavior
Rohin Shah
4y
69
28
Inferring utility functions from locally non-transitive preferences
Jan
10mo
15
102
Utility ≠ Reward
vlad_m
3y
25
23
Intertheoretic utility comparison
Stuart_Armstrong
4y
11
45
Bayesian Utility: Representing Preference by Probability Measures
Vladimir_Nesov
13y
37
69
Probability is Real, and Value is Complex
abramdemski
4y
20
49
Coherent behaviour in the real world is an incoherent concept
Richard_Ngo
3y
17
24
Quantilizers and Generative Models
Adam Jermyn
5mo
5
21
Exploring Mild Behaviour in Embedded Agents
Megan Kinniment
5mo
3
25
Quantilizers maximize expected utility subject to a conservative cost constraint
jessicata
7y
0
20
Another view of quantilizers: avoiding Goodhart's Law
jessicata
6y
1
2
Thoughts on Quantilizers
Stuart_Armstrong
5y
0
14
Quantilal control for finite MDPs
Vanessa Kosoy
4y
0
65
When to use quantilization
RyanCarey
3y
5
10
Quantilizer ≡ Optimizer with a Bounded Amount of Output
itaibn0
1y
4
19
Stable Pointers to Value III: Recursive Quantilization
abramdemski
4y
4
11
Optimization Regularization through Time Penalty
Linda Linsefors
3y
4