Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
10 posts
Inverse Reinforcement Learning
5 posts
Road To AI Safety Excellence
22
A Survey of Foundational Methods in Inverse Reinforcement Learning
adamk
3mo
0
26
Is CIRL a promising agenda?
Chris_Leong
6mo
12
70
Thoughts on "Human-Compatible"
TurnTrout
3y
35
62
Book Review: Human Compatible
Scott Alexander
2y
6
36
Learning biases and rewards simultaneously
Rohin Shah
3y
3
25
Book review: Human Compatible
PeterMcCluskey
2y
2
28
Model Mis-specification and Inverse Reinforcement Learning
Owain_Evans
4y
3
6
Biased reward-learning in CIRL
Stuart_Armstrong
4y
3
2
CIRL Wireheading
tom4everitt
5y
0
1
(C)IRL is not solely a learning process
Stuart_Armstrong
6y
0
71
RAISE is launching their MVP
3y
1
37
AI Safety Prerequisites Course: Basic abstract representations of computation
RAISE
3y
2
29
Our plan for 2019-2020: consulting for AI Safety education
RAISE
3y
17
28
IRL 1/8: Inverse Reinforcement Learning and the problem of degeneracy
RAISE
3y
2
16
RAISE AI Safety prerequisites map entirely in one post
RAISE
3y
5