model-based-reinforcement-learning

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 elegantly tackle these problems, they struggle with scalability and handling rich inputs, such as images.

Aidan Scannell, Riccardo Mereu, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin

Function-Space Bayesian Deep Learning for Sequential Learning

Neural Networks as Sparse Gaussian Processes for Sequential Learning

I will be presenting our research on bayesian deep learning for sequential learning at the International Workshop of Intelligent Autonomous Learning Systems 2023.

Aug 15, 2023 2:50 PM — 3:05 PM Darmstädter Haus and Sporthotel Walliser, Kleinwalsertal, Austria

Aidan Scannell

Neural Networks as Sparse Gaussian Processes for Sequential Learning

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

Model-based reinforcement learning under uncertainty

In this talk I’ll present our recent paper that has just been accepted into AISTATS 2023, titled Mode-Constrained Model-Based …

Feb 13, 2023 11:30 AM — 12:30 PM University of Cambridge

Aidan Scannell

Model-based reinforcement learning under uncertainty

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 techniques (e.g. Laplace approximation, MC dropout, variational inference), as well as ensemble methods, to understand why they either succeed or fail in different environments.

Aidan Scannell, Arno Solin, Joni Pajarinen

Model-based reinforcement learning under uncertainty: the importance of knowing what you don't know

In this guest lecture I present the role of uncertainty quantification in model-based RL. I show how to quantify uncertainty in …

Nov 15, 2022 2:15 PM — 4:00 PM Aalto University

Aidan Scannell

Model-based reinforcement learning under uncertainty: the importance of knowing what you don't know