AI ALIGNMENT FORUM
The Theoretical Foundations of Reward Learning
AF

The Theoretical Foundations of Reward Learning

In this sequence I provide an overview of the theoretical reward learning research agenda, including its motivating assumptions, several core results, and starting points for how to contribute to it further.

14The Theoretical Reward Learning Research Agenda: Introduction and Motivation

Joar Skalse

15d

9Partial Identifiability in Reward Learning

Joar Skalse

15d

10Misspecification in Inverse Reinforcement Learning

Joar Skalse

15d

6STARC: A General Framework For Quantifying Differences Between Reward Functions

Joar Skalse

15d

4Misspecification in Inverse Reinforcement Learning - Part II

Joar Skalse

15d

9Defining and Characterising Reward Hacking

Joar Skalse

15d

9Other Papers About the Theory of Reward Learning

Joar Skalse

15d

9How to Contribute to Theoretical Reward Learning Research

Joar Skalse

15d