collaborators

5 papers

cs.LG2026

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training

Johannes von Oswald, Nino Scherrer, Seijin Kobayashi +14

Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compu…

cs.AI2026

Multi-agent cooperation through in-context co-player inference

Marissa A. Weis, Maciej Wołczyk, Rajai Nasser +4

Achieving cooperation among self-interested agents remains a fundamental challenge in multi-agent reinforcement learning. Recent work showed that mutual cooperation can be induced…

cs.LG2025

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

Seijin Kobayashi, Yanick Schimpf, Maximilian Schlegel +12

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. Du…

cs.AI2025

Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning

Alexander Meulemans, Rajai Nasser, Maciej Wołczyk +13

The standard theory of model-free reinforcement learning assumes that the environment dynamics are stationary and that agents are decoupled from their environment, such that polici…

cs.AI2025

Multi-agent cooperation through learning-aware policy gradients

Alexander Meulemans, Seijin Kobayashi, Johannes von Oswald +6

Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation among self-interested, independent lear…