Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
12 posts
Wireheading
11 posts
Reward Functions
176
Are wireheads happy?
Scott Alexander
12y
107
49
You cannot be mistaken about (not) wanting to wirehead
Kaj_Sotala
12y
79
38
A definition of wireheading
Anja
10y
80
32
The Stamp Collector
So8res
7y
14
26
generalized wireheading
carado
1mo
7
20
Reinforcement Learner Wireheading
Nate Showell
5mo
2
20
Wireheading and discontinuity
Michele Campolo
2y
4
18
Wireheading is in the eye of the beholder
Stuart_Armstrong
3y
10
17
Wireheading as a potential problem with the new impact measure
Stuart_Armstrong
4y
20
15
Defining AI wireheading
Stuart_Armstrong
3y
9
14
Wireheading Done Right: Stay Positive Without Going Insane
9eB1
6y
2
7
Note on algorithms with multiple trained components
Steven Byrnes
6h
1
75
Seriously, what goes wrong with "reward the agent when it makes you smile"?
TurnTrout
4mo
41
47
Reward model hacking as a challenge for reward learning
Erik Jenner
8mo
1
45
A Short Dialogue on the Meaning of Reward Functions
Leon Lang
1mo
0
43
Draft papers for REALab and Decoupled Approval on tampering
Jonathan Uesato
2y
2
24
Thoughts on reward engineering
paulfchristiano
3y
30
19
An investigation into when agents may be incentivized to manipulate our beliefs.
Felix Hofstätter
3mo
0
13
$100/$50 rewards for good references
Stuart_Armstrong
1y
5
9
Why we want unbiased learning processes
Stuart_Armstrong
4y
3
8
Reward IS the Optimization Target
Carn
2mo
3
7
Reward function learning: the value function
Stuart_Armstrong
4y
0
3
Reward function learning: the learning process
Stuart_Armstrong
4y
11