Information for Jan Leike

Table of contents

Basic information

Item Value
Facebook username 100009882604264
Intelligent Agent Foundations Forum username 160

List of positions (4 positions)

Organization Title Start date End date AI safety relation Subject Employment type Source Notes
Machine Intelligence Research Institute Research Advisor 2017-03-01 position [1]
Future of Humanity Institute Research Associate [2], [3], [4]
Australian National University [5]
Google DeepMind [6], [7]

Products (0 products)

Name Creation date Description

Organization documents (0 documents)

Title Publication date Author Publisher Affected organizations Affected people Document scope Cause area Notes

Documents (2 documents)

Title Publication date Author Publisher Affected organizations Affected people Affected agendas Notes
New safety research agenda: scalable agent alignment via reward modeling 2018-11-20 Victoria Krakovna LessWrong Google DeepMind Jan Leike Recursive reward modeling, iterated amplification Blog post on LessWrong announcing the recursive reward modeling agenda. Some comments in the discussion thread clarify various aspects of the agenda, including its relation to Paul Christiano’s iterated amplification agenda, whether the DeepMind safety team is thinking about the problem of whether the human user is a safe agent, and more details about alternating quantifiers in the analogy to complexity theory. Jan Leike is listed as an affected person for this document because he is the lead author and is mentioned in the blog post, and also because he responds to several questions raised in the comments.
Scalable agent alignment via reward modeling: a research direction 2018-11-19 Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, Shane Legg arXiv Google DeepMind Recursive reward modeling, Imitation learning, inverse reinforcement learning, Cooperative inverse reinforcement learning, myopic reinforcement learning, iterated amplification, debate This paper introduces the (recursive) reward modeling agenda, discussing its basic outline, challenges, and ways to overcome those challenges. The paper also discusses alternative agendas and their relation to reward modeling.