Home
Projects
Publications
People
Join the Lab
Contact
1
Hierarchical WaveFunction Collapse
Video game developers are increasingly utilising procedural content generation (PCG) techniques in order to generate more content far …
Michael Beukman
,
Branden Ingram
,
Ireton Liu
,
Benjamin Rosman
PDF
Cite
Project
A Comparison of Visual Place Recognition Methods using a Mobile Robot in an Indoor Environment
Beatrice van Eden
,
Nicolene Botha
,
Benjamin Rosman
Cite
Overlooked Implications of the Reconstruction Loss for VAE Disentanglement
Learning disentangled representations with variational autoencoders (VAEs) is often attributed to the regularisation component of the …
Nathan Michlo
,
Richard Klein
,
Steven James
PDF
Cite
Supplementary Material
Augmentative Topology Agents For Open-ended Learning
We tackle the problem of open-ended learning by introducing a method that simultaneously evolves agents while also evolving …
Muhammad Umair Nasir
,
Michael Beukman
,
Steven James
,
Christopher Cleghorn
PDF
Cite
On The Specialization of Neural Modules
A number of machine learning models have been proposed with the goal of achieving systematic generalization: the ability to reason …
Devon Jarvis
,
Richard Klein
,
Benjamin Rosman
,
Andrew Saxe
PDF
Cite
Comparing Synthetic Tabular Data Generation Between a Probabilistic Model and a Deep Learning Model for Education Use Cases
The ability to generate synthetic data has a variety of use cases across different domains. In education research, there is a growing …
Herkulaas Combrink
,
Vukosi Marivate
,
Benjamin Rosman
PDF
Cite
Real Time In-Game Playstyle Classification Using A Hybrid Probabilistic Supervised Learning Approach
In interactive digital media, such as video games, bringing about an adaptive or personalised experience requires a mechanism for …
Lindsay John Arendse
,
Branden Ingram
,
Benjamin Rosman
PDF
Cite
Project
Reinforcement Learning in Education: A Multi-Armed Bandit Approach
Advances in reinforcement learning research have demonstrated the ways in which different agent-based models can learn how to optimally …
Herkulaas Combrink
,
Vukosi Marivate
,
Benjamin Rosman
PDF
Cite
Improving Reinforcement Learning with Ensembles of Different Learners
Different reinforcement learning (RL) methods exist to address the problem of combining multiple different learners to generate a …
Gerrie Crafford
,
Benjamin Rosman
PDF
Cite
Reducing the Planning Horizon through Reinforcement Learning
Planning is a computationally expensive process, which can limit the reactivity of autonomous agents. Planning problems are usually …
Logan Dunbar
,
Benjamin Rosman
,
Anthony G. Cohn
,
Matteo Leonetti
PDF
Cite
«
»
Cite
×