Projects

Here’s some projects that I’ve worked on over the years.

Discrete Codebook World Models featured image

Discrete Codebook World Models

In reinforcement learning (RL), world models serve as internal simulators, enabling agents to predict environment dynamics and future outcomes in order to make informed decisions. …

Aidan Scannell
Implicitly Quantized Representations for Reinforcement Learning featured image

Implicitly Quantized Representations for Reinforcement Learning

Learning representations for reinforcement learning (RL) has shown much promise for continuous control. In this project, we investigate using vector quantization to prevent …

Aidan Scannell
Function-Space Bayesian Deep Learning for Sequential Learning featured image

Function-Space Bayesian Deep Learning for Sequential Learning

Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining prior knowledge. While Gaussian processes …

Aidan Scannell
Investigating Bayesian Neural Network Dynamics Models for Model-Based Reinforcement Learning featured image

Investigating Bayesian Neural Network Dynamics Models for Model-Based Reinforcement Learning

This project seeks to evaluate and compare different approaches for learning dynamics models in model-based RL. In particular, we plan to compare different approximate inference …

Aidan Scannell
Mode-Constrained Exploration for Model-Based Reinforcement Learning featured image

Mode-Constrained Exploration for Model-Based Reinforcement Learning

This work presents a learning-based control method for navigating to a target state in unknown, or partially unknown, multimodal dynamical systems. In particular, it develops a …

Aidan Scannell
GPJax - Gaussian Processes in Jax featured image

GPJax - Gaussian Processes in Jax

Minimal Gaussian process library in JAX with a simple (custom) approach to state management.

Trajectory Optimisation in Learned Multimodal Dynamical Systems featured image

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 …

avatar
Aidan Scannell
Identifiable Mixtures of Sparse Variational Gaussian Process Experts featured image

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 …

avatar
Aidan Scannell
Probabilistic Modelling featured image

Probabilistic Modelling

I am in the process of creating Jupyter notebooks for several probabilistic models (Bayesian linear regression, Gaussian process regression) and approximate inference algorithms. …

Aidan Scannell
Model-Based Reinforcement Learning with Gaussian Processes featured image

Model-Based Reinforcement Learning with Gaussian Processes

In this work I re-implemented the PILCO algorithm in python using Tensorflow and GPflow. This work was mainly carried out for personal development and some of the implementation is …

avatar
Aidan Scannell