Publications

First Author

Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning pdf
L. McCutcheon, B. Gharesifard, S. Fallah
ICRA 2025 — IEEE International Conference on Robotics and Automation
Learns neural Lyapunov functions via off-policy RL to jointly optimise control performance and stability guarantees.

Adaptive PD Control using Deep Reinforcement Learning for Local-Remote Teleoperation with Stochastic Time Delays pdf
L. McCutcheon, S. Fallah
IROS 2023 — IEEE/RSJ International Conference on Intelligent Robots and Systems
Uses model-based RL to dynamically adapt PD controller gains online, improving robustness over fixed-gain controllers.

Preventing Policy Collapse in Continual Reinforcement Learning
L. McCutcheon, E. Chatzaroulas, S. Fallah
Under Review
Proposes a method to maintain plasticity and training stability in continual RL, preventing policy collapse across sequential tasks.

Co-Author

Meta-World+: An Improved, Standardized, RL Benchmark pdf
R. McLean, E. Chatzaroulas, L. McCutcheon, F. Roder, T. Yu, Z. He, K.R. Zentner, R. Julian, J.K. Terry, I. Woungang, N. Farsad, P.S. Castro
ICML 2025 Workshop (Spotlight) & NeurIPS 2025
Implemented multi-task optimisation baselines including PCGrad and conducted large-scale training for MT10 and MT50 benchmark experiments.

In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understanding pdf
M. Xu, E. Chatzaroulas, L. McCutcheon, A. Ahad, H. Azeem, J. Marecki, A. Anwar
NeurIPS 2024 Workshop
Supervised the project and developed the Gemini experiment pipeline.

Prediction Based Decision Making for Autonomous Highway Driving pdf
M. Yildirim, S. Mozaffari, L. McCutcheon, M. Dianati, A. Tamaddoni-Nezhad, S. Fallah
ITSC 2022 — IEEE International Conference on Intelligent Transportation Systems
Implemented noisy neural networks, the highest-performing component of the RAINBOW agent.

Reviewing

I have served as a reviewer for the following venues:

  • International Conference on Learning Representations (ICLR) 2026
  • Conference on Neural Information Processing Systems (NeurIPS) 2025
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2025
  • IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025