Inverse Reinforcement Learning

TagLast edit: 1 Dec 2021 15:12 UTC by [Error communicating with LW2 server]

Model Mis-specification and Inverse Reinforcement Learning

Owain_Evans and jsteinhardt

9 Nov 2018 15:33 UTC

30 points

3 comments16 min readLW link

Thoughts on “Human-Compatible”

TurnTrout10 Oct 2019 5:24 UTC

59 points

35 comments5 min readLW link

Learning biases and rewards simultaneously

rohinmshah6 Jul 2019 1:45 UTC

41 points

3 comments4 min readLW link

Our take on CHAI’s research agenda in under 1500 words

alexflint17 Jun 2020 12:24 UTC

100 points

19 comments5 min readLW link

Problems integrating decision theory and inverse reinforcement learning

agilecaveman8 May 2018 5:11 UTC

7 points

2 comments3 min readLW link

IRL 1/8: Inverse Reinforcement Learning and the problem of degeneracy

RAISE4 Mar 2019 13:11 UTC

20 points

2 comments1 min readLW link

(app.grasple.com)

Delegative Inverse Reinforcement Learning

Vanessa Kosoy12 Jul 2017 12:18 UTC

15 points

0 comments16 min readLW link

[Question] Can coherent extrapolated volition be estimated with Inverse Reinforcement Learning?

Jade Bishop15 Apr 2019 3:23 UTC

12 points

5 comments3 min readLW link

Cooperative Inverse Reinforcement Learning vs. Irrational Human Preferences

orthonormal18 Jun 2016 0:55 UTC

4 points

0 comments3 min readLW link

Inverse reinforcement learning on self, pre-ontology-change

Stuart_Armstrong18 Nov 2015 13:23 UTC

0 points

0 comments1 min readLW link

Biased reward-learning in CIRL

Stuart_Armstrong5 Jan 2018 18:12 UTC

8 points

3 comments7 min readLW link

CIRL Wireheading

tom4everitt8 Aug 2017 6:33 UTC

3 points

0 comments2 min readLW link

(C)IRL is not solely a learning process

Stuart_Armstrong15 Sep 2016 8:35 UTC

1 point

0 comments3 min readLW link

Book Review: Human Compatible

Scott Alexander31 Jan 2020 5:20 UTC

75 points

6 comments16 min readLW link

(slatestarcodex.com)

Book review: Human Compatible

PeterMcCluskey19 Jan 2020 3:32 UTC

37 points

2 comments5 min readLW link

(www.bayesianinvestor.com)

AXRP Episode 2 - Learning Human Biases with Rohin Shah

DanielFilan29 Dec 2020 20:43 UTC

13 points

0 comments35 min readLW link

My take on Michael Littman on “The HCI of HAI”

alexflint2 Apr 2021 19:51 UTC

58 points

4 comments7 min readLW link

AXRP Episode 8 - Assistance Games with Dylan Hadfield-Menell

DanielFilan8 Jun 2021 23:20 UTC

13 points

1 comment71 min readLW link

RAISE is launching their MVP

toonalfrink26 Feb 2019 11:45 UTC

67 points

1 comment1 min readLW link

Human-AI Collaboration

rohinmshah22 Oct 2019 6:32 UTC

42 points

7 comments2 min readLW link

(bair.berkeley.edu)

Agents That Learn From Human Behavior Can’t Learn Human Values That Humans Haven’t Learned Yet

steven046111 Jul 2018 2:59 UTC

27 points

11 comments1 min readLW link

Humans can be assigned any values whatsoever...

Stuart_Armstrong13 Oct 2017 11:29 UTC

14 points

6 comments4 min readLW link

Hardcode the AGI to need our approval indefinitely?

MichaelStJules11 Nov 2021 7:04 UTC

1 point

2 comments1 min readLW link

No comments.