What are the best published papers from outside the alignment community that are relevant to Agent Foundations?

post by Stephen Fowler (LosPolloFowler) · 2023-08-05T03:02:33.003Z · LW · GW · No comments

This is a question post.

Contents

  Answers
    8 rorygreig
    5 Martín Soto
    4 martin biehl
    2 Roman Leventov
None
No comments

I am after papers that you have stumbled across that may be relevant to the core of the understanding the existential AI alignment problem despite not having explicit links to AI alignment. 

Here are papers I have found that fit the above criteria to give you a better idea of what I'm after:

While I've used the term "agent foundations" I expect the majority of useful papers will not use terms like agency, optimization etc. 

Answers

answer by rorygreig · 2023-08-06T08:51:12.082Z · LW(p) · GW(p)

An interesting paper is The information theory of individuality, Krakauer et. al
 

answer by martin biehl · 2023-08-14T17:45:50.619Z · LW(p) · GW(p)

Interpreting Systems as Solving POMDPs: A Step Towards a Formal Understanding of Agency

https://link.springer.com/chapter/10.1007/978-3-031-28719-0_2

answer by Roman Leventov · 2023-08-06T19:25:41.539Z · LW(p) · GW(p)

"General cognitive science": Boyd et al. (2022), Goyal & Bengio (2022), Levin (2022), Fields et al. (2022), Friston et al. (2022), Ma et al. (2022), LeCun (2022) [LW · GW] (links from here [LW(p) · GW(p)]).

Also, general theories of cognitive development, e.g., Kuchling et al. 2022; Fields et al. 2022.

No comments

Comments sorted by top scores.