Aidan Scannell
Aidan Scannell
Home
Experience
Publications
Talks
Posts
Projects
CV
Contact
variational-inference
Mode-constrained Model-based Reinforcement Learning via Gaussian Processes
We present a model-based RL algorithm that constrains training to a single dynamic mode with high probability. This is a difficult problem because the mode constraint is a hidden variable associated with the environment’s dynamics. As such, it is 1) unknown a priori and 2) we do not observe its output from the environment, so cannot learn it with supervised learning.
Aidan Scannell
,
Carl Henrik Ek
,
Arthur Richards
PDF
Code
Project
Poster
Source Document
Follow
Bayesian Learning for Control in Multimodal Dynamical Systems
Mode remaining navigation (and exploration) in unknown multimodal dynamical systems via model-based reinforcement learning.
Aidan Scannell
PDF
Cite
Code
Slides
Source Document
Identifiable Mixtures of Sparse Variational Gaussian Process Experts
Mixture models are inherently unidentifiable as different combinations of component distributions and mixture weights can generate the …
Aidan Scannell
,
Carl Henrik Ek
,
Arthur Richards
PDF
Code
Project
Trajectory Optimisation in Learned Multimodal Dynamical Systems
This work presents a two-stage method to perform trajectory optimisation in multimodal dynamical systems with unknown nonlinear stochastic transition dynamics. The method finds trajectories that remain in a preferred dynamics mode where possible and in regions of the transition dynamics model that have been observed and can be predicted confidently.
Aidan Scannell
Code
Follow
Identifiable Mixtures of Sparse Variational Gaussian Process Experts
This work introduces a variational lower bound for the Mixture of Gaussian Process Experts model with a GP-based gating network based on sparse GPs. The model (and inference) are implemented in GPflow/TensorFlow.
Aidan Scannell
Code
Follow
Approximate Inference
This work implements and compares a variety of approximate inference techniques for the tasks of image de-noising (restoration) and image segmentation.
Aidan Scannell
Code
Follow
Cite
×