Christian Schroeder de Witt

Christian Schroeder de Witt

University of Oxford

H-index: 14

Europe-United Kingdom

About Christian Schroeder de Witt

Christian Schroeder de Witt, With an exceptional h-index of 14 and a recent h-index of 13 (since 2020), a distinguished researcher at University of Oxford, specializes in the field of Multi-agent Learning, Security, Safety.

His recent articles reflect a diverse array of research interests and contributions to the field:

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection

Near to Mid-term Risks and Opportunities of Open Source Generative AI

Secret Collusion Among Generative AI Agents

The Danger Of Arrogance: Welfare Equilibra As A Solution To Stackelberg Self-Play In Non-Coincidental Games

Illusory Attacks: Detectability Matters in Adversarial Attacks on Sequential Decision-Makers

Utilizing AI emulators to Model Stratospheric Aerosol Injections and their Effect on Climate

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning

Christian Schroeder de Witt Information

University

Position

___

Citations(all)

3554

Citations(since 2020)

3494

Cited By

590

hIndex(all)

14

hIndex(since 2020)

13

i10Index(all)

17

i10Index(since 2020)

17

Email

University Profile Page

University of Oxford

Google Scholar

View Google Scholar Profile

Christian Schroeder de Witt Skills & Research Interests

Multi-agent Learning

Security

Safety

Top articles of Christian Schroeder de Witt

Title

Journal

Author(s)

Publication Date

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

Alexander Rutherford

Benjamin Ellis

Matteo Gallici

Jonathan Cook

Andrei Lupu

...

2024/5/6

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection

AAMAS 2024 (Oral)

Linas Nasvytis

Kai Sandbrink

Jakob Foerster

Tim Franzmeyer*

Christian Schroeder de Witt*

2024/1/1

Near to Mid-term Risks and Opportunities of Open Source Generative AI

arXiv preprint arXiv:2404.17047

Francisco Eiras

Aleksandar Petrov

Bertie Vidgen

Christian Schroeder de Witt

Fabio Pizzati

...

2024/4/25

Secret Collusion Among Generative AI Agents

arXiv preprint arXiv:2402.07510

Sumeet Ramesh Motwani

Mikhail Baranchuk

Martin Strohmeier

Vijay Bolina

Philip HS Torr

...

2024/2/12

The Danger Of Arrogance: Welfare Equilibra As A Solution To Stackelberg Self-Play In Non-Coincidental Games

arXiv preprint arXiv:2402.01088

Jake Levi

Chris Lu

Timon Willi

Christian Schroeder de Witt

Jakob Foerster

2024/2/2

Illusory Attacks: Detectability Matters in Adversarial Attacks on Sequential Decision-Makers

Tim Franzmeyer

Stephen Marcus McAleer

Joao F Henriques

Jakob Nicolaus Foerster

Philip Torr

...

2024

Utilizing AI emulators to Model Stratospheric Aerosol Injections and their Effect on Climate

EGU General Assembly Conference Abstracts

Eshaan Agrawal

Christian Schroder de Witt

2023/5

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning

ICLR 2023

Yat Long Lo

Christian Schroeder de Witt

Samuel Sokota

Jakob Nicolaus Foerster

Shimon Whiteson

2023/3/19

JaxMARL: Multi-Agent RL Environments in JAX

AAMAS 2024

Alexander Rutherford

Benjamin Ellis

Matteo Gallici

Jonathan Cook

Andrei Lupu

...

2023/11/16

A Perfect Collusion Benchmark: How can AI agents be prevented from colluding with information-theoretic undetectability?

Sumeet Ramesh Motwani

Mikhail Baranchuk

Lewis Hammond

Christian Schroeder de Witt

2023/10/31

Perfectly Secure Steganography Using Minimum Entropy Coupling

Christian Schroeder de Witt*

Samuel Sokota*

J Zico Kolter

Jakob Foerster

Martin Strohmeier

2023

Computing Low-Entropy Couplings for Large-Support Distributions

Samuel Sokota

Dylan Sam

Christian Schroeder de Witt

Spencer Compton

Jakob Nicolaus Foerster

...

2023/10/13

Bayesian Exploration Networks

arXiv preprint arXiv:2308.13049

Mattie Fellows

Brandon Kaplowitz

Christian Schroeder de Witt

Shimon Whiteson

2023/8/24

Biological Evolution and Genetic Algorithms: Exploring the Space of Abstract Tile Self-Assembly

arXiv preprint arXiv:2205.15311

Christian Schroeder de Witt

2022/5/28

Revealing robust oil and gas company macro-strategies using deep multi-agent reinforcement learning

arXiv preprint arXiv:2211.11043

Dylan Radovic

Lucas Kruitwagen

Christian Schroeder de Witt

Ben Caldecott

Shane Tomlinson

...

2022/11/20

Mirror learning: A unifying framework of policy optimisation

Jakub Grudzien

Christian A Schroeder De Witt

Jakob Foerster

2022/6/28

(Private)-Retroactive Carbon Pricing [(P) ReCaP]: A Market-based Approach for Climate Finance and Risk Assessment

arXiv preprint arXiv:2205.00666

Yoshua Bengio

Prateek Gupta

Dylan Radovic

Maarten Scholl

Andrew Williams

...

2022/5/2

Generalized beliefs for cooperative AI

Darius Muglich

Luisa M Zintgraf

Christian A Schroeder De Witt

Shimon Whiteson

Jakob Foerster

2022/6/28

Amortized Rejection Sampling in Universal Probabilistic Programming

Saeid Naderiparizi

Adam Scibior

Andreas Munk

Mehrdad Ghadiri

Atilim Gunes Baydin

...

2022/5/3

Model-free opponent shaping

Christopher Lu

Timon Willi

Christian A Schroeder De Witt

Jakob Foerster

2022/6/28

See List of Professors in Christian Schroeder de Witt University(University of Oxford)

Co-Authors

H-index: 131
Philip Torr

Philip Torr

University of Oxford

H-index: 64
Shimon Whiteson

Shimon Whiteson

University of Oxford

H-index: 21
Atılım Güneş Baydin

Atılım Güneş Baydin

University of Oxford

H-index: 20
Wendelin Böhmer

Wendelin Böhmer

Technische Universiteit Delft

H-index: 16
Bei Peng

Bei Peng

University of Oxford

H-index: 13
Nantas Nardelli

Nantas Nardelli

University of Oxford

academic-engine