Massimiliano (Max) Tamborski

Hi, I am Max, a PhD student in the CamRAL Group at the University of Cambridge (Gonville & Caius College), supervised by Rika Antonova and David Abel. My research is generously supported by a full scholarship from the Computer Science Department and a grant from the Advanced Research and Invention Agency (ARIA).

I recently completed a Master of Informatics at the University of Edinburgh, and was a member of the Autonomous Agents Research Group from 2021. During my time there, I was fortunate to be supervised by David Abel and Stefano Albrecht. I also studied at the University of Pennsylvania.

I am interested in real-world autonomous agents through the lens of reinforcement learning, bounded agency, and the co-design of hardware and policy learning. In particular, I’m interested in:

(a) How can robots adapt their behaviour depending on the resources they have?
(b) Given fixed resources, how can robots jointly evolve their control policies and physical designs to maximise their performance across tasks and environments?

I am always open to new ideas and collaborations. If you’re interested in bounded agency, RL, continual learning, robotics, or anything related, please don’t hesitate to send me an email. I’d love to chat!

news

Jul 11, 2025	🏆 Honoured to receive the Howe Undergraduate Prize as the top-ranked graduate across all AI-related degree programmes within the School of Informatics at the University of Edinburgh.
May 03, 2025	✈️ Memory Allocation in Resource-Constrained Reinforcement Learning accepted as a spotlight at RLDM 2025!

selected publications

Memory Allocation in Resource-Constrained Reinforcement Learning

Massimiliano Tamborski and David Abel

Conference on Reinforcement Learning and Decision Making, 2025

(Spotlight: given to 5.9% of papers)

arXiv Bib PDF

@article{tamborski2025memory,
  title = {Memory Allocation in Resource-Constrained Reinforcement Learning},
  author = {Tamborski, Massimiliano and Abel, David},
  journal = {Conference on Reinforcement Learning and Decision Making},
  year = {2025},
  spotlight = {(Spotlight: given to 5.9% of papers)},
}