Johannes Forkel — accepted AI-conference papers

2026

Recurrent Structural Policy Gradient for Partially Observable Mean Field Games

Clarisse Wibault, Sebastian Towers, Tiphaine Wibault, Juan Duque, Johannes Forkel, George Whittle +6

ICML 2026spotlight

Mean Field Games (MFGs) provide a principled framework for modeling interactions in large populations models: at scale, population dynamics become deterministic, with uncertainty entering only through aggregate shocks, or *common noise*. However, algorithmic progress has been limited since model-fre…

Cited by 0 Source ↗Scholar ↗

2025

Expected Return Symmetries

Darius Muglich, Johannes Forkel, Elise van der Pol, Jakob Nicolaus Foerster

ICLR 2025poster

Symmetry is an important inductive bias that can improve model robustness and generalization across many deep learning domains. In multi-agent settings, a priori known symmetries have been shown to address a fundamental coordination failure mode known as mutually incompatible symmetry breaking; e.g.…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

LILO: Learning to Reason at the Frontier of Learnability

Thomas Foster, Anya Sims, Johannes Forkel, Jakob Nicolaus Foerster

NeurIPS 2025poster

Reinforcement learning is widely adopted in post-training large language models, especially for reasoning-style tasks such as maths questions. However, as we show, most existing methods will provably fail to learn from questions that are too hard, where the model always fails, or too easy, where the…

Cited by 0 Source ↗Scholar ↗