Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
73 posts
Reinforcement Learning
Inverse Reinforcement Learning
Wireheading
Reward Functions
Road To AI Safety Excellence
28 posts
AI Capabilities
Definitions
Stag Hunt
Goals
Prompt Engineering
PaLM
EfficientZero
218
Reward is not the optimization target
TurnTrout
4mo
97
158
Are wireheads happy?
Scott Alexander
12y
107
92
Book Review: Human Compatible
Scott Alexander
2y
6
84
Jitters No Evidence of Stupidity in RL
1a3orn
1y
18
77
Seriously, what goes wrong with "reward the agent when it makes you smile"?
TurnTrout
4mo
41
66
A definition of wireheading
Anja
10y
80
63
RAISE is launching their MVP
3y
1
63
My take on Michael Littman on "The HCI of HAI"
Alex Flint
1y
4
58
The Stamp Collector
So8res
7y
14
56
Thoughts on "Human-Compatible"
TurnTrout
3y
35
51
Draft papers for REALab and Decoupled Approval on tampering
Jonathan Uesato
2y
2
49
Book review: Human Compatible
PeterMcCluskey
2y
2
46
Learning biases and rewards simultaneously
Rohin Shah
3y
3
45
Reinforcement Learning: A Non-Standard Introduction (Part 1)
royf
10y
19
281
Is AI Progress Impossible To Predict?
alyssavance
7mo
38
194
EfficientZero: How It Works
1a3orn
1y
42
139
EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised
gwern
1y
52
71
When AI solves a game, focus on the game's mechanics, not its theme.
Cleo Nardo
27d
7
69
Misc. questions about EfficientZero
Daniel Kokotajlo
1y
17
51
Competitive programming with AlphaCode
Algon
10mo
37
50
Do Humans Want Things?
lukeprog
11y
53
44
Compact vs. Wide Models
Vaniver
4y
5
43
Note on Terminology: "Rationality", not "Rationalism"
Vladimir_Nesov
11y
51
39
Will we run out of ML data? Evidence from projecting dataset size trends
Pablo Villalobos
1mo
12
39
An Agent is a Worldline in Tegmark V
komponisto
4y
12
35
The Problem With The Current State of AGI Definitions
Yitz
6mo
22
29
Disambiguating "alignment" and related notions
David Scott Krueger (formerly: capybaralet)
4y
21
23
Remaking EfficientZero (as best I can)
Hoagy
5mo
9