Two papers accepted at ICML

We are pleased to announce that the following two papers were accepted at the International Conference on Machine Learning (ICML).

Congratulations to the authors!

1. Unsupervised Partner Design Enables Robust Ad-hoc Teamwork

   Constantin Ruhdorfer, Matteo Bortoletto, Victor Oei, Anna Penzkofer, Andreas Bulling

   Proc. International Conference on Machine Learning (ICML), 2026.

   Abstract BibTeX Project Spotlight

   We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly and selects them adaptively based on a learnability criterion, removing the need for pre-trained partner populations or manual parameter tuning. We show that this simple mechanism enables effective partner diversity and can be extended to joint partner-environment selection when a procedural level generator is available. Across Level-Based Foraging, Overcooked-AI, and the Overcooked Generalisation Challenge, UPD consistently outperforms both population-based and population-free baselines. In a human-AI user study, agents trained with UPD achieve higher returns and are rated as more adaptive, more human-like, and less frustrating than existing approaches.

   @inproceedings{ruhdorfer26_icml, title = {Unsupervised Partner Design Enables Robust Ad-hoc Teamwork}, shorttitle = {{UPD}}, author = {Ruhdorfer, Constantin and Bortoletto, Matteo and Oei, Victor and Penzkofer, Anna and Bulling, Andreas}, year = {2026}, booktitle = {Proc. International Conference on Machine Learning (ICML)} }

2. MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning

   Tristan Tomilin, Luka Boogaard, Samuel Garcin, Constantin Ruhdorfer, Bram Grooten, Fabrice Kusters, Yali Du, Andreas Bulling, Mykola Pechenizkiy, Meng Fang

   Proc. International Conference on Machine Learning (ICML), 2026.

   Abstract BibTeX Project

   Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied. Despite the motivation of lifelong learning, most continual RL papers consider only 3-10 sequential tasks, as CPU-bound environments make longer sequences impractical. Meanwhile, continual learning in cooperative multi-agent settings remains largely unexplored. To address these gaps, we introduce MEAL (Multi-agent Environments for Adaptive Learning), the first benchmark for continual multi-agent RL. By leveraging JAX and GPU acceleration, MEAL enables training on sequences of 100 tasks on a single GPU in a few hours. We find that long task sequences reveal failure modes that do not appear at smaller scales.

   @inproceedings{tomilin26_icml, title = {MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning}, author = {Tomilin, Tristan and van den Boogaard, Luka and Garcin, Samuel and Ruhdorfer, Constantin and Grooten, Bram and Kusters, Fabrice and Du, Yali and Bulling, Andreas and Pechenizkiy, Mykola and Fang, Meng}, year = {2026}, booktitle = {Proc. International Conference on Machine Learning (ICML)} }

Here are some related news you might like to read next:

• New paper accepted at SciSec
• New paper accepted at FG
• New paper accepted at ACL
• New paper accepted at CVPRW
• New paper accepted at LREC