Built on

“Utility Indifference”, 2010
Stuart Armstrong · 2010
Earlier work this paper cites.
“Corrigibility”
Nate Soares, Benja Fallenstein, Eliezer Yudkowsky and Stuart Armstrong · 2015
Earlier work this paper cites.

Similar

“The Off-Switch Game”
Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel and Stuart Russell · 2017
Cited alongside, same era.

Then

“Should Robots be Obedient?”, 2017
Original
Smitha Milli, Dylan Hadfield-Menell, Anca Dragan and Stuart Russell · 2017
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2017

Incorrigibility in the CIRL Framework

Carey, Ryan

Understand

A value learning system has incentives to follow shutdown instructions, assuming the shutdown instruction provides information (in the technical sense) about which actions lead to valuable outcomes.

However, this assumption is not robust to model mis-specification (e.g., in the case of programmer errors).
We demonstrate this by presenting some Supervised POMDP scenarios in which errors in the parameterized reward function remove the incentive to follow shutdown commands.
These difficulties parallel those discussed by Soares et al.