Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
56 posts
Value Learning
The Pointers Problem
Meta-Philosophy
Metaethics
Kolmogorov Complexity
Philosophy
Perceptual Control Theory
11 posts
Inverse Reinforcement Learning
Book Reviews
99
The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables
johnswentworth
2y
43
76
Some Thoughts on Metaphilosophy
Wei_Dai
3y
27
71
Clarifying "AI Alignment"
paulfchristiano
4y
82
66
Parsing Chris Mingard on Neural Networks
Alex Flint
1y
27
62
Preface to the sequence on value learning
Rohin Shah
4y
6
56
Conclusion to the sequence on value learning
Rohin Shah
3y
20
54
What is ambitious value learning?
Rohin Shah
4y
28
54
Humans can be assigned any values whatsoever…
Stuart_Armstrong
4y
26
54
Policy Alignment
abramdemski
4y
25
54
Normativity
abramdemski
2y
11
53
Intuitions about goal-directed behavior
Rohin Shah
4y
15
53
Don't design agents which exploit adversarial inputs
TurnTrout
1mo
61
52
The easy goal inference problem is still hard
paulfchristiano
4y
19
50
Different perspectives on concept extrapolation
Stuart_Armstrong
8mo
7
69
[Book Review] "The Alignment Problem" by Brian Christian
lsusr
1y
16
59
Thoughts on "Human-Compatible"
TurnTrout
3y
35
53
Human-AI Collaboration
Rohin Shah
3y
7
48
Learning biases and rewards simultaneously
Rohin Shah
3y
3
39
Model Mis-specification and Inverse Reinforcement Learning
Owain_Evans
4y
3
34
Agents That Learn From Human Behavior Can't Learn Human Values That Humans Haven't Learned Yet
steven0461
4y
11
18
Delegative Inverse Reinforcement Learning
Vanessa Kosoy
5y
0
17
Cooperative Inverse Reinforcement Learning vs. Irrational Human Preferences
orthonormal
6y
0
4
CIRL Wireheading
tom4everitt
5y
0
1
(C)IRL is not solely a learning process
Stuart_Armstrong
6y
0
0
Inverse reinforcement learning on self, pre-ontology-change
Stuart_Armstrong
7y
0