| Item | Value |
|---|---|
| Country | United Kingdom |
| Website | https://deepmind.com/ |
| Source | [1] |
| Agendas | Recursive reward modeling |
Hover over a name to see the position and date range. This table only includes positions where at least the start date is known. The positions count can count the same person multiple times if they held different positions; similarly, the list of staff may include the same person multiple times if they held more than one position during a single year. For each year, a person is included if they were at the organization for any part of the year; this means the actual staff count at any point during the year can be lower (or higher, if some staff held multiple positions in a single year).
The following table lists some dates and people who were at the organization on the given date (namely, the start of the year). The table may not list every person who worked for the organization (e.g. they could have joined and left in the middle of a single year). This table excludes associates, interns, advisors, and board members.
This table shows the full change history of positions. Each row corresponds to at least one addition or removal of a position. Additions are in green and subtractions are in red. If a position name changed, it is listed simultaneously as an addition (of the new name) and removal (of the old name) and colored yellow. Additionally there are faded variants of each color for visited links.
| Date | Number of positions | Number of positions added | Number of positions removed | Positions added | Positions removed |
|---|---|---|---|---|---|
| 13 | 13 | 0 | Andrew Lefrancq, Chris Maddison, Christiana Figueres, Diane Coyle, Edward W. Felten, James Manyika, Jan Leike, Jeffrey D. Sachs, Laurent Orseau, Nick Bostrom, Thore Graepel, Tom Everitt, Victoria Krakovna | ||
| 2010-09-23 | 16 | 3 | 0 | Demis Hassabis, Mustafa Suleyman, Shane Legg | |
| 2016-01-01 | 17 | 1 | 0 | Pedro A. Ortega | |
| 2017-03-01 | 18 | 1 | 0 | Miljan Martic | |
| 2017-10-04 | 20 | 2 | 0 | Sean Legassick, Verity Harding | |
| 2018-02-01 | 21 | 1 | 0 | Vishal Maini | |
| 2020-10-01 | 22 | 1 | 0 | Miljan Martic | |
| 2020-10-31 | 21 | 0 | -1 | Miljan Martic |
| Person | Title | Start date | End date | AI safety relation | Subject | Employment type | Source | Notes |
|---|---|---|---|---|---|---|---|---|
| Chris Maddison | Research Scientist | position | technical research | [2] | One of the Open Philanthropy Project 2018 AI Fellows. | |||
| Laurent Orseau | Research Scientist | [3], [4], [5], [6], [7], [8], [9] | ||||||
| Victoria Krakovna | Research Scientist | [10], [8], [9] | ||||||
| Nick Bostrom | DeepMind Ethics & Society Fellow | [11] | ||||||
| Diane Coyle | DeepMind Ethics & Society Fellow | [11] | ||||||
| Edward W. Felten | DeepMind Ethics & Society Fellow | [11] | ||||||
| Christiana Figueres | DeepMind Ethics & Society Fellow | [11] | ||||||
| James Manyika | DeepMind Ethics & Society Fellow | [11] | ||||||
| Jeffrey D. Sachs | DeepMind Ethics & Society Fellow | [11] | ||||||
| Sean Legassick | Head of DeepMind Ethics & Society | 2017-10-04 | [12], [13] | |||||
| Verity Harding | Head of DeepMind Ethics & Society | 2017-10-04 | [12], [13] | |||||
| Demis Hassabis | Co-Founder and CEO | 2010-09-23 | [14], [15] | |||||
| Mustafa Suleyman | Co-Founder and Head of Applied AI | 2010-09-23 | [14], [15] | |||||
| Shane Legg | Co-Founder and Chief Scientist | 2010-09-23 | [14], [15], [16], [8], [9] | |||||
| Miljan Martic | Reserach Engineer | 2017-03-01 | 2020-10-31 | AGI organization | [16], [8], [17] | |||
| Miljan Martic | Senior Reserach Engineer | 2020-10-01 | AGI organization | [16], [8], [17] | ||||
| Jan Leike | [16], [8] | |||||||
| Tom Everitt | [8] | |||||||
| Andrew Lefrancq | [8] | |||||||
| Pedro A. Ortega | Research Scientist | 2016-01-01 | position | technical research | full-time | [8], [18], [19], [20], [21] | ||
| Vishal Maini | Strategic Communications Manager | 2018-02-01 | position | popularization | [22], [23], [24] | |||
| Thore Graepel | [25] |
| Name | Creation date | Description |
|---|
| Title | Publication date | Author | Publisher | Affected organizations | Affected people | Document scope | Cause area | Notes |
|---|
| 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. |