I am a 3rd year PhD student at The University of Edinburgh, advised by Amos Storkey as a member of the Bayesian and Neural Systems Group in the Institute for Adaptive and Neural Computation.
I am interested in getting reinforcement learning into the real world by focusing on:
- Offline settings (and variations therein)
- Representation learning for high-dimensional observation spaces
- Model-based methods
- Off-policy methods

SELECTED PUBLICATIONS
()♔: co-first authors
Click title for arXiv link, authors for BibTeX
Title | Authors | Venue |
---|---|---|
Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning | (Samuel Garcin & Trevor McInroe)♔, Pablo Samuel Castro, Christopher G. Lucas, David Abel, Prakash Panangaden, Stefano V Albrecht | ICLR |
Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning | Trevor McInroe, Adam Jelley, Stefano V. Albrecht, Amos Storkey | RLC |
Conditional Mutual Information for Disentangled Representations in Reinforcement Learning | Mhairi Dunion, Trevor McInroe, Kevin Luck, Josiah Hanna, Stefano V. Albrecht | NeurIPS (Spotlight) |
Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning | Mhairi Dunion, Trevor McInroe, Kevin Sebastian Luck, Josiah P. Hanna, Stefano V. Albrecht | ICLR |
LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots | Dongge Han, Trevor McInroe, Adam Jelley, Stefano V. Albrecht, Peter Bell, Amos Storkey | COLING |
Efficient Offline Reinforcement Learning: The Critic is Critical | Adam Jelley, Trevor McInroe, Sam Devlin, Amos Storkey | ICML (Workshop) |