Dr. Cameron Foale
Head of Information Technology
Dr Cameron Foale is a Lecturer in information technology at Federation University Australia. Dr Foale’s research expertise includes digital capture of stringed instrument acoustics, biopsychosocial health data, reinforcement learning, and safe and explainable artificial intelligence.
Cameron is currently working on research projects in machine learning for cross-talk minimisation, Bayesian approaches to multiobjective reinforcement learning, and multi-channel effects processing for stringed instruments. Cameron is an active member of Federation Learning Agents Group (FLAG) and has been part of several of the University’s flagship research centres, as well as being involved in the Internet Commerce Security Laboratory (ICSL).
Cameron completed his PhD at the University of Ballarat in 2010 in the field of acoustics for virtual environments, and subsequently entered the IT industry as a web and games developer in the digital education sector. Cameron returned to teaching and research at Federation University in 2014.
Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning
A conceptual framework for externally-influenced agents: an assisted reinforcement learning review
A NetHack Learning Environment Language Wrapper for Autonomous Agents
Human engagement providing evaluative and informative advice for interactive reinforcement learning
Persistent rule-based interactive reinforcement learning
Scalar Reward is Not Enough JAAMAS Track
Discrete-to-deep reinforcement learning methods
Neural networks are effective function approximators, but hard to train in the reinforcement...
Scalar reward is not enough: a response to Silver, Singh, Precup and Sutton (2021)
Statistical Calibration of Long-Term Reanalysis Data for Australian Fire Weather Conditions
An evaluation methodology for interactive reinforcement learning with simulated users
Interactive reinforcement learning methods utilise an external information source to evaluate...
Language Representations for Generalization in Reinforcement Learning
Levels of explainable artificial intelligence for human-aligned conversational explanations
Over the last few years there has been rapid research growth into eXplainable Artificial...
Potential-based multiobjective reinforcement learning approaches to low-impact agents for AI safety
The concept of impact-minimisation has previously been proposed as an approach to addressing the...
The impact of environmental stochasticity on value-based multiobjective reinforcement learning
A common approach to address multiobjective problems using reinforcement learning methods is to...
Discrete-to-Deep Supervised Policy Learning An effective training method for neural reinforcement learning
An Empirical Study of Reward Structures for Actor-Critic Reinforcement Learning in Air Combat Manoeuvring Simulation
Reinforcement learning techniques for solving complex problems are resource-intensive and take a...
Towards Machine Learning approach for Digital-Health intervention program
Digital-Health intervention (DHI) are used by health care providers to promote engagement...
Human-aligned artificial intelligence is a multiobjective problem
As the capabilities of artificial intelligence (AI) systems improve, it becomes important to...
Modeling neurocognitive reaction time with Gamma distribution
As a broader effort to build a holistic biopsychosocial health metric, reaction time data...
Non-functional regression: A new challenge for neural networks
This work identifies an important, previously unaddressed issue for regression based on neural...
Relevance of Frequency of Heart-Rate Peaks as Indicator of 'Biological' Stress Level
The biopsychosocial (BPS) model proposes that health is best understood as a combination of...
SoniFight: Software to Provide Additional Sonification Cues to Video Games for Visually Impaired Players
SoniFight is utility software designed to provide additional sonification cues to video games,...
Softmax exploration strategies for multiobjective reinforcement learning
Despite growing interest over recent years in applying reinforcement learning to multiobjective...
Steering approaches to Pareto-optimal multiobjective reinforcement learning
For reinforcement learning tasks with multiple objectives, it may be advantageous to learn...
Caliko: An Inverse Kinematics Software Library Implementation of the FABRIK Algorithm
The Caliko library is an implementation of the FABRIK (Forward And Backward Reaching Inverse...
Reinforcement learning of pareto-optimal multiobjective policies using steering
Portal-based Sound Propagation for First-Person Computer Games
First-person computer games are a popular modern video game genre. A new method is proposed, the...