LESSWRONG
LW

Basic Foundations for Agent Models

May 16, 2022 by johnswentworth
62Against Time in Agent Models
Ω
johnswentworth
3y
Ω
13
90Writing Causal Models Like We Write Programs
Ω
johnswentworth
5y
Ω
11
217Utility Maximization = Description Length Minimization
Ω
johnswentworth
4y
Ω
50
88Optimization at a Distance
Ω
johnswentworth
3y
Ω
16
31Bits of Optimization Can Only Be Lost Over A Distance
Ω
johnswentworth
3y
Ω
18
74The "Measuring Stick of Utility" Problem
Ω
johnswentworth
3y
Ω
25
66Distributed Decisions
Ω
johnswentworth
3y
Ω
6
156What's General-Purpose Search, And Why Might We Expect To See It In Trained ML Systems?
Ω
johnswentworth
3y
Ω
18