Aidan Scannell

Introduction World models equip agents (e.g., humanoid robots) with internal simulators of their environments.

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.

Learning representations for reinforcement learning (RL) has shown much promise for continuous control.

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

This project seeks to evaluate and compare different approaches for learning dynamics models in model-based RL.

After the first lockdown here in the UK, I decided that building a keyboard would make a good lockdown 2.0 project.

I am developing a minimal Python package for implementing Gaussian process models in Python using JAX.

Over the last few years I have been trying to find the best tools for managing my CV/resume.

This work presents a two-stage method to perform trajectory optimisation in multimodal dynamical systems with unknown nonlinear stochastic transition dynamics.

This work derives a novel variational lower bound for the mixture of Gaussian process experts model with a GP based gating network based on sparse GPs.

This is a short post detailing how I installed Emacs and configured an environment for maintaining multiple configurations (on my MacBook Pro).

I’ve wanted to write a blog post about my journey with repetitive strain injury (RSI) for quite a while now.

In this post I want to walk through Gaussian process regression; both the maths and a simple 1-dimensional python implementation.

Hello and welcome to my blog.