The list doesn’t include anything in the way of game theory, social choice, or mechanism design, which is going to be crucial for an AI that interacts with other agents or tries to aggregate preferences.
Relevant book recommendations (all available at links as pdfs):
Essentials of Game Theory by Leyton-Brown and Shoham. (Gated, might be accessible through a university connection, otherwise easily searchable)
On this note, perhaps very time-sensitively-relevant, Coursera’s online course on Game Theory has just started. It’s a 7-week course that claims to cover all the strong basics. It’s quite interactive, too, and seems more optimized for efficient learning than traditional university courses.
If anyone’s interested, you can still jump right in (probably until the 13th or 14th-ish), the Week 1 material is probably easy to cover in two hours (or maybe three depending on how carefully and rigorously you want to do the problem set) for most LWers.
The course description and syllabus should tell you everything else I haven’t said (see second link above).
Agree with this. I haven’t read those books, but I know that Public Choice III also contains 100> pages of thorough discussion about how the choice of a voting system influences the way that preferences get aggregated under those systems. Something like that seems like a must-read for Friendliness researchers.
The list doesn’t include anything in the way of game theory, social choice, or mechanism design, which is going to be crucial for an AI that interacts with other agents or tries to aggregate preferences.
Relevant book recommendations (all available at links as pdfs):
Essentials of Game Theory by Leyton-Brown and Shoham. (Gated, might be accessible through a university connection, otherwise easily searchable)
A Course in Game Theory by Osbourne and Rubinstein (requires free registration)
Multi-agent Systems: Algorithmic, Game-Theoretic, and Logical Foundations by Shoham and Leyton-Brown.
Algorithmic Game Theory edited by Nisan, Roughgarden, Tardis, and Varizani.
On this note, perhaps very time-sensitively-relevant, Coursera’s online course on Game Theory has just started. It’s a 7-week course that claims to cover all the strong basics. It’s quite interactive, too, and seems more optimized for efficient learning than traditional university courses.
If anyone’s interested, you can still jump right in (probably until the 13th or 14th-ish), the Week 1 material is probably easy to cover in two hours (or maybe three depending on how carefully and rigorously you want to do the problem set) for most LWers.
The course description and syllabus should tell you everything else I haven’t said (see second link above).
I’ve joined—thanks.
Agree with this. I haven’t read those books, but I know that Public Choice III also contains 100> pages of thorough discussion about how the choice of a voting system influences the way that preferences get aggregated under those systems. Something like that seems like a must-read for Friendliness researchers.
The first link isn’t free. It costs $5.
Ah, I didn’t notice since I could access it through a university connection. I’ll edit to note that.