428 citations · 1.2k across the 32 of their papers we have counts for
34 papers
MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning
Brandon Gary Kaplowitz, Osaze James Obahor, Christian Schroeder de Witt
World models improve sample efficiency by training policies on imagined trajectories, but their usefulness depends on learning representations that capture the information needed f…
Exploring the Cryptographic Limits of Transformer Networks
Stefan Domunco, Andis Draguns, Philip Torr +2
In recent work it has been shown that colluding AI agents can use steganographic methods to exchange malicious information. Whether a transformer can implement steganographic metho…
Computing Low-Entropy Couplings for Large-Support Distributions
Samuel Sokota, Dylan Sam, Christian Schroeder de Witt +3
Minimum-entropy coupling (MEC) -- the process of finding a joint distribution with minimum entropy for given marginals -- has applications in areas such as causality and steganogra…
Near to Mid-term Risks and Opportunities of Open-Source Generative AI
Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +21
In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for thes…
Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection
Linas Nasvytis, Kai Sandbrink, Jakob Foerster +2
While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environm…
The Danger Of Arrogance: Welfare Equilibra As A Solution To Stackelberg Self-Play In Non-Coincidental Games
Jake Levi, Chris Lu, Timon Willi +2
The increasing prevalence of multi-agent learning systems in society necessitates understanding how to learn effective and safe policies in general-sum multi-agent environments aga…
JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
Alexander Rutherford, Benjamin Ellis, Matteo Gallici +18
Benchmarks are crucial in the development of machine learning algorithms, with available environments significantly influencing reinforcement learning (RL) research. Traditionally,…
Bayesian Exploration Networks
Mattie Fellows, Brandon Kaplowitz, Christian Schroeder de Witt +1
Bayesian reinforcement learning (RL) offers a principled and elegant approach for sequential decision making under uncertainty. Most notably, Bayesian agents do not face an explora…
Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning
Yat Long Lo, Christian Schroeder de Witt, Samuel Sokota +2
By enabling agents to communicate, recent cooperative multi-agent reinforcement learning (MARL) methods have demonstrated better task performance and more coordinated behavior. Mos…
Revealing Robust Oil and Gas Company Macro-Strategies using Deep Multi-Agent Reinforcement Learning
Dylan Radovic, Lucas Kruitwagen, Christian Schroeder de Witt +3
The energy transition potentially poses an existential risk for major international oil companies (IOCs) if they fail to adapt to low-carbon business models. Projections of energy…
Discovered Policy Optimisation
Chris Lu, Jakub Grudzien Kuba, Alistair Letcher +3
Tremendous progress has been made in reinforcement learning (RL) over the past decade. Most of these advancements came through the continual development of new algorithms, which we…
Perfectly Secure Steganography Using Minimum Entropy Coupling
Christian Schroeder de Witt, Samuel Sokota, J. Zico Kolter +2
Steganography is the practice of encoding secret information into innocuous content in such a manner that an adversarial third party would not realize that there is hidden meaning.…
Equivariant Networks for Zero-Shot Coordination
Darius Muglich, Christian Schroeder de Witt, Elise van der Pol +2
Successful coordination in Dec-POMDPs requires agents to adopt robust strategies and interpretable styles of play for their partner. A common failure mode is symmetry breaking, whe…
Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks
Tim Franzmeyer, Stephen McAleer, João F. Henriques +4
Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attack…
Generalized Beliefs for Cooperative AI
Darius Muglich, Luisa Zintgraf, Christian Schroeder de Witt +2
Self-play is a common paradigm for constructing solutions in Markov games that can yield optimal policies in collaborative settings. However, these policies often adopt highly-spec…
Biological Evolution and Genetic Algorithms: Exploring the Space of Abstract Tile Self-Assembly
Christian Schroeder de Witt
A physically-motivated genetic algorithm (GA) and full enumeration for a tile-based model of self-assembly (JaTAM) is implemented using a graphics processing unit (GPU). We observe…
(Private)-Retroactive Carbon Pricing [(P)ReCaP]: A Market-based Approach for Climate Finance and Risk Assessment
Yoshua Bengio, Prateek Gupta, Dylan Radovic +5
Insufficient Social Cost of Carbon (SCC) estimation methods and short-term decision-making horizons have hindered the ability of carbon emitters to properly correct for the negativ…
Mirror Learning: A Unifying Framework of Policy Optimisation
Jakub Grudzien Kuba, Christian Schroeder de Witt, Jakob Foerster
Modern deep reinforcement learning (RL) algorithms are motivated by either the generalised policy iteration (GPI) or trust-region learning (TRL) frameworks. However, algorithms tha…
Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS
Christian Schroeder de Witt, Yongchao Huang, Philip H. S. Torr +1
Cyber attacks are increasing in volume, frequency, and complexity. In response, the security community is looking toward fully automating cyber defense systems using machine learni…
Communicating via Markov Decision Processes
Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl +6
We consider the problem of communicating exogenous information by means of Markov decision process trajectories. This setting, which we call a Markov coding game (MCG), generalizes…
A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings
Eltayeb Ahmed, Luisa Zintgraf, Christian A. Schroeder de Witt +1
In this work we explore an auxiliary loss useful for reinforcement learning in environments where strong performing agents are required to be able to navigate a spatial environment…
RainBench: Towards Global Precipitation Forecasting from Satellite Imagery
Christian Schroeder de Witt, Catherine Tong, Valentina Zantedeschi +5
Extreme precipitation events, such as violent rainfall and hail storms, routinely ravage economies and livelihoods around the developing world. Climate change further aggravates th…
Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?
Christian Schroeder de Witt, Tarun Gupta, Denys Makoviichuk +4
Most recently developed approaches to cooperative multi-agent reinforcement learning in the \emph{centralized training with decentralized execution} setting involve estimating a ce…
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Shariq Iqbal, Christian A. Schroeder de Witt, Bei Peng +3
Multi-agent settings in the real world often involve tasks with varying types and quantities of agents and non-agent entities; however, common patterns of behavior often emerge amo…