RSS

RAISE

Karma: 121

Road to AI Safety Excellence. Our mission is to make studying AI as easy as possible, in whatever way. Right now, we’re developing an online course for AI Safety.

More info: https://​​www.aisafety.info/​​ . Inspiration: https://​​distill.pub/​​2017/​​research-debt/​​ and https://​​slatestarcodex.com/​​2017/​​11/​​09/​​ars-longa-vita-brevis/​​

AI Safety Pr­ereq­ui­sites Course: Ba­sic ab­stract rep­re­sen­ta­tions of computation

RAISE13 Mar 2019 19:38 UTC
28 points
2 comments1 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)

Our plan for 2019-2020: con­sult­ing for AI Safety education

RAISE3 Jun 2019 16:51 UTC
18 points
15 comments3 min readLW link

RAISE AI Safety pre­req­ui­sites map en­tirely in one post

RAISE17 Jul 2019 8:57 UTC
18 points
5 comments38 min readLW link

IRL 2/​8: Miti­gat­ing de­gen­er­acy: mul­ti­ple experimentation

RAISE11 Mar 2019 13:33 UTC
13 points
0 comments1 min readLW link
(app.grasple.com)

IDA 1-4/​14: Prob­lem Statement

RAISE7 Mar 2019 14:02 UTC
8 points
0 comments1 min readLW link
(app.grasple.com)

IRL 7/​8: Gen­er­al­iz­ing hu­man-robot co­op­er­a­tion: Co­op­er­a­tive IRL

RAISE15 Apr 2019 10:13 UTC
7 points
0 comments1 min readLW link
(app.grasple.com)

IRL 5/​8: Max­i­mum Causal En­tropy IRL

RAISE4 Apr 2019 10:53 UTC
7 points
2 comments1 min readLW link
(app.grasple.com)

[Link] IDA: 11-14/​14: Fu­ture Directions

RAISE28 Mar 2019 18:56 UTC
6 points
0 comments1 min readLW link

IRL 3/​8: Miti­gat­ing de­gen­er­acy: fea­ture matching

RAISE18 Mar 2019 20:15 UTC
6 points
0 comments1 min readLW link
(app.grasple.com)

IRL 4/​8: Max­i­mum En­tropy IRL and Bayesian IRL

RAISE25 Mar 2019 22:07 UTC
4 points
0 comments1 min readLW link
(app.grasple.com)

IDA 5-8/​14: Ap­proval Directed Agents

RAISE14 Mar 2019 23:58 UTC
4 points
0 comments1 min readLW link
(app.grasple.com)

[Link] IDA 9/​14: The Scheme

RAISE21 Mar 2019 18:28 UTC
4 points
0 comments1 min readLW link

IRL 6/​8: Query­ing the hu­man: Ac­tive Re­ward Learning

RAISE8 Apr 2019 13:49 UTC
4 points
0 comments1 min readLW link
(app.grasple.com)

IRL 8/​8: Gen­er­a­tive Ad­ver­sar­ial Imi­ta­tion Learning

RAISE22 Apr 2019 15:02 UTC
2 points
0 comments1 min readLW link
(app.grasple.com)