Leonard Hinckeldey

L[DOT]HINCKELDEY[AT]ED.AC.UK

I’m a second-year PhD researcher driven by an overarching goal: to build autonomous agents in simulation that can collaborate with any human in the real world. My current focus is on developing reinforcement learning methods that are robust when coordinating with any potential partner — whether another AI agent or, ultimately, a human. This problem setting is known as ad-hoc teamwork, or sometimes zero-shot coordination.

My PhD is at the University of Edinburgh’s Centre for AI in Assistive Autonomy, where I’m supervised by Prof. Subramanian Ramamoorthy. I’m also a member of MARBLE (Multi-Agent, Reinforcement, Behaviour and Learning), where I co-organise the RL & Agents Reading Group. I receive additional support from the Honda Research Institute, with mentorship from Fan Zhang and Michael Gienger.

Before my PhD, I completed a social data science Master’s at the LSE, and before that an undergraduate degree in Economics.

news

May 25, 2026	Our paper Probing Dec-POMDP Reasoning in Cooperative MARL will be presented at AAMAS 2026!
Aug 05, 2025	🇨🇦 Attending the Reinforcement Learning Conference (RLC) in Edmonton, Canada!

selected publications

AAMAS

Probing Dec-POMDP Reasoning in Cooperative MARL

Kale-ab Tessera, Leonard Hinckeldey, Riccardo Zamboni, and 2 more authors

In The 25th International Conference on Autonomous Agents and Multi-Agent Systems, 2026

Bib PDF

@inproceedings{tessera2026probing,
  title = {Probing Dec-{POMDP} Reasoning in Cooperative {MARL}},
  author = {Tessera, Kale-ab and Hinckeldey, Leonard and Zamboni, Riccardo and Abel, David and Storkey, Amos},
  booktitle = {The 25th International Conference on Autonomous Agents and Multi-Agent Systems},
  year = {2026},
  url = {https://openreview.net/forum?id=gSK8tR7du3},
}

RLC Workshop

Assistax: A Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics

Leonard Hinckeldey, Elliot Fosong, Elle Miller, and 6 more authors

2025

Bib PDF

@misc{hinckeldey2025assistaxhardwareacceleratedreinforcementlearning,
  title = {Assistax: A Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics},
  author = {Hinckeldey, Leonard and Fosong, Elliot and Miller, Elle and Rubavicius, Rimvydas and McInroe, Trevor and Wollstadt, Patricia and Wiebel-Herboth, Christiane B. and Ramamoorthy, Subramanian and Albrecht, Stefano V.},
  year = {2025},
  eprint = {2507.21638},
  archiveprefix = {arXiv},
  primaryclass = {cs.AI},
  url = {https://arxiv.org/abs/2507.21638},
}