paper-with-me

홈 › Papers

Unsupervised Partner Design Enables Robust Ad-hoc Teamwork

2025-08-08 · Constantin Ruhdorfer, Matteo Bortoletto, Victor Oei, Anna Penzkofer, Andreas Bulling arxiv

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 achieves strong performance compared to 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 all evaluated baseline methods.

📄 PDF Abstract BibTeX arXiv:2508.06336

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

A Minimax Approach to Ad Hoc Teamwork

2025-02-04 · Victor Villin, Thomas Kleine Buening, Christos Dimitrakakis

We propose a minimax-Bayes approach to Ad Hoc Teamwork (AHT) that optimizes policies against an adversarial prior over partners, explicitly accounting for uncertainty about partners at time of deployment. Unlike existing…

ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork

2025-05-29 · Caroline Wang, Arrasy Rahman, Jiaxun Cui, Yoonchang Sung 외

Developing AI agents capable of collaborating with previously unseen partners is a fundamental generalization challenge in multi-agent learning, known as Ad Hoc Teamwork (AHT). Existing AHT approaches typically adopt a t…

Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prior Collaboration

2026-06-17 · Taewoon Kim, Emma van Zoelen, Mark Neerincx arxiv

Effective human-robot teamwork requires robots to adapt to partners, situations, and task dynamics from the start of an interaction. In the MATRX Urban Search and Rescue (USAR) environment, people can externalize collabo…

Graph Representation Learning

Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agents

2023-08-18 · Arrasy Rahman, Jiaxun Cui, Peter Stone

Robustly cooperating with unseen agents and human partners presents significant challenges due to the diverse cooperative conventions these partners may adopt. Existing Ad Hoc Teamwork (AHT) methods address this challeng…

Diversity

Modeling Latent Partner Strategies for Adaptive Zero-Shot Human-Agent Collaboration

2025-07-07 · Benjamin Li, Shuyang Shi, Lucia Romero, Huao Li 외 arxiv

In collaborative tasks, being able to adapt to your teammates is a necessary requirement for success. When teammates are heterogeneous, such as in human-agent teams, agents need to be able to observe, recognize, and adap…