Christian Schroeder de Witt
Christian Schroeder de Witt
Home
About Me
Experience
Honors, Awards & Grants
CV
Publications
Teaching
Press
Contact
Consulting
Industry Collaboration
Outreach Request
Other
Light
Dark
Automatic
3
Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS
we suggest a novel reinforcement learning setting that can be used to efficiently generate arbitrary adversarial perturbations using deep multi-agent reinforcement learning.
Christian Schroeder de Witt
,
Huang, Yongchao
,
Strohmeier, Martin
PDF
Cite
(Private)-Retroactive Carbon Pricing [(P)ReCaP]: A Market-based Approach for Climate Finance and Risk Assessment
We used deep multi-agent reinforcement learning to solve an energy systems wargame wherein players simulate IOC decision-making.
Yoshua Bengio
,
Prateek Gupta
,
Dylan Radovic
,
Maarten Scholl
,
Andrew Williams
,
Christian Schroeder de Witt
,
Tianyu Zhang
,
Yang Zhang
PDF
Cite
Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control
This paper introduces Multi-Agent Mujoco, an easily extensible multi-agent benchmark suite for robotic control in continuous action spaces
Christian Schroeder de Witt
,
Tarun Gupta
,
Denys Makoviichuk
,
Viktor Makoviychuk
,
Philip HS Torr
,
Mingfei Sun
,
Shimon Whiteson
PDF
Cite
Is Independent Learning all you need in the Starcraft Multi-Agent Challenge?
We demonstrate that, despite its various theoretical shortcomings, Independent PPO (IPPO), a form of independent learning in which each agent simply estimates its local value function, can perform just as well as or better than state-of-the-art joint learning approaches.
Christian Schroeder de Witt
,
Tarun Gupta
,
Denys Makoviichuk
,
Viktor Makoviychuk
,
Philip HS Torr
,
Mingfei Sun
,
Shimon Whiteson
PDF
Cite
Revealing Robust Oil and Gas Company Macro-Strategies using Deep Multi-agent Reinforcement Learning
We used deep multi-agent reinforcement learning to solve an energy systems wargame wherein players simulate IOC decision-making.
Dylan Radovic
,
Lucas Kruitwagen
,
Christian Schroeder de Witt
,
Ben Caldecott
,
Shane Tomlinson
,
Mark Workman
PDF
Cite
Hijacking Malaria Simulators with Probabilistic Programming
We introduce an approach that allows one to treat a large class of population-based epidemiology simulators as probabilistic generative models.
Bradley Gram-Hansen
,
Christian Schroeder de Witt
,
Tom Rainforth
,
Philip HS Torr
,
Yee Whye Teh
,
Atılım Güneş Baydin
PDF
Cite
Safe Screening for Support Vector Machines
We present the first safe removal bound for data points whichdoes not rely on spectral properties of the kernel matrix.
Julian Zimmert
,
Christian Schroeder de Witt
,
Giancarlo Kerg
,
Marius Kloft
PDF
Cite
Cite
×