Trevor McInroe

I am a 2nd year PhD student at The University of Edinburgh in the Bayesian and Neural Systems group advised by Amos Storkey and the Autonomous Agents Research Group advised by Stefano Albrecht.

My goal is to bring reinforcement learning agents to the real world.

Prior to my PhD, I worked for five years in industry on problems like vision for autonomous vehicles at Toyota Connected and completed my master’s at Northwestern University.

selected publications

2024

RLC

Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning

Trevor McInroe, Adam Jelley, Stefano V. Albrecht, and Amos Storkey

In Reinforcement Learning Conference (RLC), 2024

arXiv Bib

@inproceedings{ptgood,
  title = {Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning},
  author = {McInroe, Trevor and Jelley, Adam and Albrecht, Stefano V. and Storkey, Amos},
  booktitle = {Reinforcement Learning Conference (RLC)},
  year = {2024},
}

Workshop

Efficient Offline Reinforcement Learning: The Critic is Critical

Adam Jelley, Trevor McInroe, Sam Devlin, and Amos Storkey

In Workshop on Aligning Reinforcement Learning Experimentalists and Theorists, 2024

arXiv Bib

@inproceedings{criticiscritical,
  title = {Efficient Offline Reinforcement Learning: The Critic is Critical},
  author = {Jelley, Adam and McInroe, Trevor and Devlin, Sam and Storkey, Amos},
  booktitle = {Workshop on Aligning Reinforcement Learning Experimentalists and Theorists},
  year = {2024},
}

2023

NeurIPS Spotlight

Conditional Mutual Information for Disentangled Representations in Reinforcement Learning

Mhairi Dunion, Trevor McInroe, Kevin Sebastian Luck, Josiah Hanna, and Stefano V. Albrecht

In Conference on Neural Information Processing Systems (NeurIPS), 2023

arXiv Bib Code

@inproceedings{cmid,
  title = {Conditional Mutual Information for Disentangled Representations in Reinforcement Learning},
  author = {Dunion, Mhairi and McInroe, Trevor and Luck, Kevin Sebastian and Hanna, Josiah and Albrecht, Stefano V.},
  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
  year = {2023},
}

ICLR

Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning

Mhairi Dunion, Trevor McInroe, Kevin Sebastian Luck, Josiah P. Hanna, and Stefano V. Albrecht

In International Conference on Learning Representations (ICLR), 2023

arXiv Bib Code

@inproceedings{ted,
  title = {Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning},
  author = {Dunion, Mhairi and McInroe, Trevor and Luck, Kevin Sebastian and Hanna, Josiah P. and Albrecht, Stefano V.},
  year = {2023},
  booktitle = {International Conference on Learning Representations (ICLR)},
}