Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
30 posts
Reinforcement Learning
Wireheading
Reward Functions
11 posts
AI Capabilities
EfficientZero
Tradeoffs
13
Note on algorithms with multiple trained components
Steven Byrnes
7h
1
233
Reward is not the optimization target
TurnTrout
4mo
97
83
Scaling Laws for Reward Model Overoptimization
leogao
2mo
11
37
A Short Dialogue on the Meaning of Reward Functions
Leon Lang
1mo
0
77
Towards deconfusing wireheading and reward maximization
leogao
3mo
7
80
Seriously, what goes wrong with "reward the agent when it makes you smile"?
TurnTrout
4mo
41
42
Four usages of "loss" in AI
TurnTrout
2mo
18
38
Conditioning, Prompts, and Fine-Tuning
Adam Jermyn
4mo
9
87
Jitters No Evidence of Stupidity in RL
1a3orn
1y
18
23
Value extrapolation vs Wireheading
Stuart_Armstrong
6mo
1
66
My take on Michael Littman on "The HCI of HAI"
Alex Flint
1y
4
27
$100/$50 rewards for good references
Stuart_Armstrong
1y
5
38
Big picture of phasic dopamine
Steven Byrnes
1y
18
53
Draft papers for REALab and Decoupled Approval on tampering
Jonathan Uesato
2y
2
44
Will we run out of ML data? Evidence from projecting dataset size trends
Pablo Villalobos
1mo
12
81
Evaluations project @ ARC is hiring a researcher and a webdev/engineer
Beth Barnes
3mo
7
38
It matters when the first sharp left turn happens
Adam Jermyn
2mo
9
108
We have achieved Noob Gains in AI
phdead
7mo
21
212
EfficientZero: How It Works
1a3orn
1y
42
144
EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised
gwern
1y
52
77
OpenAI Solves (Some) Formal Math Olympiad Problems
Michaël Trazzi
10mo
26
98
The alignment problem in different capability regimes
Buck
1y
12
70
Misc. questions about EfficientZero
Daniel Kokotajlo
1y
17
25
Remaking EfficientZero (as best I can)
Hoagy
5mo
9
8
Epistemic Strategies of Safety-Capabilities Tradeoffs
adamShimi
1y
0