1

Model Predictive-Actor Critic Reinforcement Learning for Dexterous Manipulation

Dexterous multi-fingered robotic hands represent a promising solution for robotic manipulators to perform a wide range of complex …

Muhammad Omer, Rami Ahmed, Benjamin Rosman, Sharief F. Babikir

A Framework for Undergraduate Data Collection Strategies for Student Support Recommendation Systems in Higher Education

Understanding which student support strategies mitigate dropout and improve student retention is an important part of modern higher …

Herkulaas Combrink, Vukosi Marivate, Benjamin Rosman

Knowledge Transfer using Model-Based Deep Reinforcement Learning

Deep reinforcement learning has recently been adopted for robot behavior learning, where robot skills are acquired and adapted from …

Tlou Boloka, Ndivhuwo Makondo, Benjamin Rosman

A Boolean Task Algebra for Reinforcement Learning

The ability to compose learned skills to solve new tasks is an important property for lifelong-learning agents. In this work we …

Geraud Nangue Tasse, Steven James, Benjamin Rosman

Utilising Uncertainty for Efficient Learning of Likely-Admissible Heuristics

Likely-admissible heuristics have previously been introduced as heuristics that are admissible with some probability. While such …

Ofir Marom, Benjamin Rosman

Discovery of Influence between Processes Represented by Hidden Markov Models

Learning the underlying structure between processes is a common problem found in the sciences, however not much work is dedicated …

Ritesh Ajoodha, Benjamin Rosman

Learning Portable Representations for High-Level Planning

We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous …

Steven James, Benjamin Rosman, George Konidaris

Combining Primitive DQNs for Improved Reinforcement Learning in Minecraft

We ask whether a reinforcement learning agent learns better by first learning the skills to perform smaller tasks in a complex …

Matthew Reynard, Herman Kamper, Herman A Engelbrecht, Benjamin Rosman

Confident in the Crowd: Bayesian Inference to Improve Data Labelling in Crowdsourcing

With the increased interest in machine learning and big data problems, the need for large amounts of labelled data has also grown. …

Pierce Burke, Richard Klein

Inter-and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition

Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields …

Nishai Kooverjee, Steven James, Terence Van Zyl