1

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

Learning Options from Demonstration using Skill Segmentation

We present a method for learning options from segmented demonstration trajectories. The trajectories are first segmented into skills …

Matthew Cockcroft, Shahil Mawjee, Steven James, Pravesh Ranchod

Quantisation and Pruning for Neural Network Compression and Regularisation

Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered …

Kimessha Paupamah, Steven James, Richard Klein