LESSWRONG
Wikitags
LW

Subscribe
Discussion0
1

Satisficer

Subscribe
Discussion0
1
Written by plex last updated 28th Dec 2020

A Satisficer aims to reach a set level of utility rather than maximizing utility. It is a proposed optimization process to the open Other-izer problem.

Video explaining Satisficers vs Maximizers (and why satisficers are still dangerous)

Posts tagged Satisficer
38Satisficers want to become maximisers
Stuart_Armstrong
14y
70
85Satisficers Tend To Seek Power: Instrumental Convergence Via Retargetability
Ω
TurnTrout
4y
Ω
8
70Game Theory without Argmax [Part 1]
Ω
Cleo Nardo
2y
Ω
18
45Principled Satisficing To Avoid Goodhart
JenniferRM
10mo
2
44[Aspiration-based designs] 1. Informal introduction
Ω
B Jacobs, Jobst Heitzig, Simon Fischer, Simon Dima
1y
Ω
4
32In Praise of Maximizing – With Some Caveats
David Althaus
10y
19
31Game Theory without Argmax [Part 2]
Cleo Nardo
2y
14
25Why don't quantilizers also cut off the upper end of the distribution?
QΩ
Alex_Altair, Jeremy Gillen
2y
QΩ
2
20Hedonic Loops and Taming RL
Ω
beren
2y
Ω
14
47How to safely use an optimizer
Ω
Simon Fischer
1y
Ω
21
38Aspiration-based Q-Learning
Ω
Clément Dumas, Jobst Heitzig
2y
Ω
5
18[Aspiration-based designs] 2. Formal framework, basic algorithm
Ω
Jobst Heitzig, Simon Dima, Simon Fischer
1y
Ω
2
12AISC project: SatisfIA – AI that satisfies without overdoing it
Jobst Heitzig
2y
0
10Defining a limited satisficer
Stuart_Armstrong
10y
11
8Creating a satisficer
Stuart_Armstrong
10y
26
Load More (15/20)
Add Posts