1

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 …
PDF Cite Project
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 …
PDF Cite
Sentiment Analysis as an Indicator to Evaluate Gender disparity on Sexual Violence Tweets in South Africa
South Africa has one of the highest rates of sexual violence in the world, and with this technology era being the information age, it …
PDF Cite
Understanding Structure of Concurrent Actions
Whereas most work in reinforcement learning (RL) ignores the structure or relationships between actions, in this paper we show that …
PDF Cite
Anticipatory Bayesian Policy Selection for Online Adaptation of Collaborative Robots to Unknown Human Types
As a key component of collaborative robots (cobots) working with humans, existing decision-making approaches try to model the …
PDF Cite
Composing Value Functions in Reinforcement Learning
An important property for lifelong-learning agents is the ability to combine existing skills to solve new unseen tasks. In general, …
PDF Cite Project Supplementary Material
A Comparison Between Fully Connected and Deconvolutional Layers for Road Segmentation from Satellite Imagery
Semantic segmentation using fully convolutional networks has quickly become a popular solution as they provide very accurate per pixel …
PDF Cite
An Overview of Robot Vision
Robot vision is an interdisciplinary field that deals with how robots can be made to gain high-level understanding from digital images …
PDF Cite
Towards Improving Incremental Learning of Manipulator Kinematics with Inter-robot Knowledge Transfer
This paper investigates the improvement of learning sensorimotor models for developmental robots, in particular robot arm kinematics …
PDF Cite
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a …
PDF Cite Supplementary Material