This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Inverse Reinforcement Learning
Edit Wiki
History
Stub
Posts tagged
Inverse Reinforcement Learning
Most Relevant
9
57
Thoughts on "Human-Compatible"
Ω
TurnTrout
10mo
Ω
35
9
34
Model Mis-specification and Inverse Reinforcement Learning
Ω
Owain_Evans
,
jsteinhardt
2y
Ω
3
9
2
CIRL Wireheading
Ω
tom4everitt
3y
Ω
0
2
77
Book Review: Human Compatible
Scott Alexander
6mo
6
2
39
Book review: Human Compatible
PeterMcCluskey
7mo
2
2
23
IRL 1/8: Inverse Reinforcement Learning and the problem of degeneracy
RAISE
1y
2
2
19
Problems integrating decision theory and inverse reinforcement learning
agilecaveman
2y
2
2
18
Biased reward-learning in CIRL
Stuart_Armstrong
3y
1
2
15
Delegative Inverse Reinforcement Learning
Ω
Vanessa Kosoy
3y
Ω
0
2
14
Can coherent extrapolated volition be estimated with Inverse Reinforcement Learning?
Q
Jade Bishop
1y
Q
5
2
2
Cooperative Inverse Reinforcement Learning vs. Irrational Human Preferences
Ω
orthonormal
4y
Ω
0
2
0
Inverse reinforcement learning on self, pre-ontology-change
Ω
Stuart_Armstrong
5y
Ω
0
2
0
(C)IRL is not solely a learning process
Ω
Stuart_Armstrong
4y
Ω
0
1
85
RAISE is launching their MVP
toonalfrink
1y
1
1
44
Learning biases and rewards simultaneously
Ω
rohinmshah
1y
Ω
3