RSS

orthonormal

Karma: 17,776

Value Learn­ing for Ir­ra­tional Toy Models

orthonormalMay 15, 2017, 8:55 PM
0 points
0 comments2 min readLW link

HCH as a mea­sure of manipulation

orthonormalMar 11, 2017, 3:02 AM
1 point
7 comments1 min readLW link

Cen­sor­ing out-of-do­main representations

orthonormalFeb 1, 2017, 4:09 AM
3 points
5 comments1 min readLW link

Vec­tor-Valued Re­in­force­ment Learning

orthonormalNov 1, 2016, 12:21 AM
2 points
1 comment4 min readLW link

Co­op­er­a­tive In­verse Re­in­force­ment Learn­ing vs. Ir­ra­tional Hu­man Preferences

orthonormalJun 18, 2016, 12:55 AM
17 points
2 comments3 min readLW link

Proof Length and Log­i­cal Coun­ter­fac­tu­als Revisited

orthonormalFeb 10, 2016, 6:56 PM
3 points
5 comments4 min readLW link

Ob­sta­cle to modal op­ti­mal­ity when you’re be­ing modalized

orthonormalAug 29, 2015, 8:41 PM
4 points
0 comments2 min readLW link

A sim­ple model of the Löbstacle

orthonormalJun 11, 2015, 4:23 PM
4 points
0 comments2 min readLW link

Agent Si­mu­lates Pre­dic­tor us­ing Se­cond-Level Oracles

orthonormalJun 6, 2015, 10:08 PM
5 points
0 comments2 min readLW link

Agents that can pre­dict their New­comb predictor

orthonormalMay 19, 2015, 10:17 AM
1 point
4 comments3 min readLW link

Mo­dal Bar­gain­ing Agents

orthonormalApr 16, 2015, 10:19 PM
14 points
20 comments5 min readLW link

[Clear­ing out my Drafts folder] Ra­tion­al­ity and De­ci­sion The­ory Cur­ricu­lum Idea

orthonormalMar 23, 2015, 10:54 PM
6 points
0 comments2 min readLW link

An In­tro­duc­tion to Löb’s The­o­rem in MIRI Research

orthonormalMar 23, 2015, 10:22 PM
29 points
27 comments2 min readLW link

Wel­come, new con­trib­u­tors!

orthonormalMar 23, 2015, 9:53 PM
6 points
2 comments3 min readLW link

A toy model of a cor­rigi­bil­ity problem

orthonormalMar 22, 2015, 7:33 PM
5 points
1 comment1 min readLW link
(www.overleaf.com)

New fo­rum for MIRI re­search: In­tel­li­gent Agent Foun­da­tions Forum

orthonormalMar 20, 2015, 12:35 AM
53 points
43 comments1 min readLW link

Fo­rum Digest: Up­date­less De­ci­sion Theory

orthonormalMar 20, 2015, 12:22 AM
15 points
0 comments4 min readLW link

Meta- the goals of this forum

orthonormalMar 10, 2015, 8:16 PM
4 points
1 comment3 min readLW link

Pro­posal: Model­ing goal sta­bil­ity in ma­chine learning

orthonormalMar 3, 2015, 1:31 AM
2 points
2 comments3 min readLW link

An In­tro­duc­tion to Löb’s The­o­rem in MIRI Research

orthonormalJan 22, 2015, 8:35 PM
4 points
0 comments1 min readLW link