Publications

Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen (2024). Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning. In 4th Annual Conference on Learning for Dynamics and Control (L4DC).

Aidan Scannell

Equal contribution

, Riccardo Mereu

Equal contribution

, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin (2024). Function-space Parameterization of Neural Networks for Sequential Learning. In The Twelth International Conference on Learning Representations (ICLR).

Aidan Scannell

Equal contribution

, Riccardo Mereu

Equal contribution

, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin (2023). Sparse Function-space Representation of Neural Networks. In ICML 2023 Workshop on Duality Principles for Modern Machine Learning.

Aidan Scannell, Carl Henrik Ek, Arthur Richards (2023). Mode-constrained Model-based Reinforcement Learning via Gaussian Processes. In 26th International Conference on Artificial Intelligence and Statistics (AISTATS).

Aidan Scannell (2022). PhD Thesis: Bayesian Learning for Control in Multimodal Dynamical Systems. University of Bristol.

Aidan Scannell, Carl Henrik Ek, Arthur Richards (2021). Identifiable Mixtures of Sparse Variational Gaussian Process Experts. UK RAS CDT Conference.

Aidan Scannell, Carl Henrik Ek, Arthur Richards (2021). Trajectory Optimisation in Learned Multimodal Dynamical Systems via Latent-ODE Collocation. In IEEE International Conference on Robotics and Automation (ICRA).