RSS

IAFF-User-111

Karma: 16

Look­ing for Recom­men­da­tions RE UDT vs. bounded com­pu­ta­tion /​ meta-rea­son­ing /​ op­por­tu­nity cost?

IAFF-User-1118 Nov 2017 22:58 UTC
0 points
1 comment1 min readLW link

Min­i­miz­ing Em­pow­er­ment for Safety

IAFF-User-1119 Feb 2017 4:45 UTC
0 points
2 comments1 min readLW link

Does UDT *re­ally* get counter-fac­tu­ally mugged?

IAFF-User-1114 Feb 2017 21:46 UTC
0 points
7 comments1 min readLW link

Learn­ing Im­pact in RL

IAFF-User-1114 Feb 2017 21:42 UTC
1 point
6 comments1 min readLW link

Some work on con­nect­ing UDT and Re­in­force­ment Learning

IAFF-User-11117 Dec 2015 23:58 UTC
4 points
5 comments1 min readLW link
(drive.google.com)

UDT from an RL perspective

IAFF-User-11117 Dec 2015 23:48 UTC
0 points
0 comments1 min readLW link
(drive.google.com)