Professor Peter Vamplew
Associate Dean Research
Campus
Mt Helen Campus
Biography
Professor Peter Vamplew’s information technology expertise focuses on artificial intelligence, particularly reinforcement learning. Reinforcement learning is a powerful methodology for developing AI agents which learn through experience to carry out sequential decision-making tasks, such as controlling industrial processes.
Peter is currently researching variations on reinforcement learning algorithms to make them effective problems with multiple conflicting objectives. He is also investigating how these methods can contribute to improving the explainability and safety of autonomous AI systems. Peter’s research has been published widely in highly-ranked international journals.
Peter co-leads the Australian Responsible Autonomous Agents Collective, a multi-institution research group which focuses on reinforcement learning and related topics. He is also a senior member of the Future of Life Institute’s Existential AI Risk research community.
Peter has been a Professor in Information Technology at Federation University Australia since 2023. He was previously an Associate Professor at Federation (2014–2023), and Senior Lecturer at the University of Ballarat (2005–2014). Prior to that he was a lecturer within the computing discipline at the University of Tasmania (1991–2005) where he received his PhD in 1996.
Fields of research
- Autonomous agents and multiagent systems
- Reinforcement learning
- Fairness, accountability, transparency, trust and ethics of computer systems
Available for
HDR Supervision
Professional Comment
HDR Examiner
More about Peter
Qualifications
- Bachelor of Arts and Bachelor of Science (Honours), Federation University
- PhD, University of Tasmania
- Graduate Certificate in Leadership in Education and Training, Victoria University
Areas of interest
- Reinforcement learning
- Multi-objective reinforcement learning
- AI safety and alignment
Areas of expertise
Peter is a world leader in the extension of reinforcement learning algorithms to problems with multiple conflicting objectives. He is very interested in deploying these techniques to real-world applications.
Grants
- Vamplew, Foale and Dazeley, Multi-objective Reinforcement Learning for AI Safety, 2023–2026, Founders Pledge ($126,500)
- Vamplew, Foale and Dazeley, Development of software to support research in multi-objective reinforcement learning for AI safety, 2023–2024, Berkley Existential Risk Institute ($12,500)
- Iqbal Gondal and Peter Vamplew, Program Analysis Techniques to Defeat Virtualized Software Obfuscations, 2020–2022, 2020 Defence Science Institute's Research Higher Degree (RHD) Student Grant ($15,000)
- Dazeley, Bethel, Wilkin, Vamplew, Aryal, Foale and Anderson, Analysis of Human-Machine Teams in Adversarial Environments, 2021–2022, Air Force Office of Scientific Research and Defence Science and Technology Group Australian Autonomy Initiative ($367,875)
- Vamplew, Dazeley, Foale and Aryal, Modelling Adversary Intent Using Multiobjective Reinforcement Learning, 2020–2021, Defence Science and Technology Group Operations Research Collaboration ($97,431)
- Vamplew, Foale, Dazeley and Johnson, Investigating Multi-Agent Learning with Multiple and Uncertain Objectives, 2020, Defence Science and Technology Group AI for Decision-Making Initiative ($20,000)
- Robinson, Thompson, Dahlhaus (CeRDI), Vamplew, Machine Learning to Extract Maximum Value from Soil and Crop Variability, 2020–2022, Grains Research and Development Corporation ($1,000,000)
- Gondal, Kamruzzaman, Karmakar, Vamplew, March, Watters, Spam email categorization using natural language processing and attention-embedded deep learning, 2019, Oceania Cyber Security Centre – POC Program ($40,000)
- Iqbal Gondal and Peter Vamplew, Evolved Similarity in Malware, 2019, Defence Science and Technology Group Scholarship (Project-Based) Funding Agreement ($10,000)
- Britt Klein (PI) + other FedUni researchers including P Vamplew, Wellbeing Track and Change, 2019–2021, WorkSafe ($1,278,141)
- Iqbal Gondal, Peter Vamplew, Adil Bagirov, Joarder Kamruzzaman, A Multi-Layered approach to Detecting Malicious Mobile Advertising, 2018–2019, Oceania Cyber Security Centre - POC Program ($78,540)
- Peter Vamplew, Richard Dazeley, Cameron Foale and Michael Papasimeon (DSTG), Multi-Objective Reinforcement Learning in Dynamic Team Based Adversarial Games, 2017–2020, Defence Science and Technology Group Scholarship (Project-Based) Funding Agreement ($45,000)
- Peter Vamplew, Rosemary Torney, Iqbal Gondal and Manuel Cebrian (Data61), Applying Machine Learning to identify Online Sexual Predators, 2016–2017, Data61 Collaborative Research Program ($16,034)
- Robert Layton, Iqbal Gondal, Peter Vamplew, Load Optimisation for Delivery, 2014, Department of Transport ($61,800)
Awards
- 2021: Federation University Vice Chancellor’s Award for Excellence (Research Excellence) “Acknowledging world-leading research in the area of multi-objective reinforcement learning, a sub-field of artificial intelligence.”
Current
- Master’s student, Federation University, 'Optimizing Cheese Production with Machine Learning ', associate supervisor.
- PhD student, Federation University, 'Adversarial Machine Learning in Safety-Critical IoT Systems ', principal supervisor. 
- PhD student, Deakin University, 'Artificial Intelligence for Pollen Monitoring ', co-supervisor.  
- PhD student, Deakin University, 'Out-of-distribution Detection in Reinforcement Learning Systems ', co-supervisor. 
- PhD student, UNSW, 'Ensemble Reinforcement Learning with Dynamic Weights ', co-supervisor. 
- PhD student, Deakin University, 'AI Apology: an Apologetic Approach to Socially Responsible AI Agents ', co-supervisor. 
- PhD student, Deakin University, 'Addressing the deadly triad in deep reinforcement learning ', co-supervisor.
Past
- PhD student, Federation University, 'In-paddock variability of plant available water', associate supervisor. 
- PhD student, Federation University, 'Measuring the effectiveness of explanations of the decisions of artificial intelligence (AI) algorithms ', principal supervisor.
- PhD student, Federation University, 'Single- and Multiobjective Reinforcement Learning in Dynamic Adversarial Games ', principal supervisor. 
- PhD student, Federation University, 'Adventures in software engineering: plugging HCI & acessibility gaps with open source solutions ', principal supervisor.
- PhD student, Federation University, 'Intelligent Zero-Day Intrusion Detection Framework for Internet of Things ', associate supervisor.
- PhD student, Federation University, 'Techniques for the reverse engineering of banking malware ', associate supervisor.
- PhD student, Federation University, 'Fraud detection for online banking for scalable and distributed data ', associate supervisor.
- PhD student, Federation University, 'Rule-based interactive assisted reinforcement learning ', associate supervisor.
- PhD student, Federation University, 'Video game classification in Australia: Does it enable parents to make informed game choices for their children ', associate supervisor.
- PhD student, Federation University, 'Assessing productive soil-landscapes in Victoria using digital soil mapping ', associate supervisor.
- PhD student, Federation University, 'Application of psycholinguistic features to authorship profiling for first language, gender and age group ', principal supervisor.
- PhD student, Federation University, 'Causes, magnitude and implications of Griefing in Massively Multiplayer Online Role-Playing Games ', associate supervisor.
- PhD student, Federation University, 'Internet banking fraud detection using prudent analysis ', associate supervisor.
- PhD student, Federation University, 'Static code analysis of data-driven applications through common lingua and the Semantic Web technologies ', associate supervisor.
- PhD student, Federation University, 'The Directional Propagation Cache: Real-time Acoustics Simulation for Immersive Computer Games ', principal supervisor.
- PhD student, Federation University, 'Regulatory network discovery using heuristics ', principal supervisor.
- Master’s student, Federation University, 'Unsupervised Colour Texture Segmentation Using Markov Random Fields ', principal supervisor.
- Master’s student, Federation University, 'Reinforcement Learning on the AIBO Robot ', associate supervisor.
- PhD student, University of Tasmania, 'Escaping the Bounds of Generality: Unbounded Biobjective Optimisation ', principal supervisor.
- PhD student, University of Tasmania, 'A Biologically-Inspired Model for Robot Navigation ', principal supervisor.
- Master’s student, University of Tasmania, 'Multi-user virtual reality ', associate supervisor.
- Master’s student, University of Tasmania, 'The influence of specific entry devices for navigation in virtual environments on the ability to gather spatial knowledge ', principal supervisor.
- PhD student, University of Tasmania, 'The construction of training signals from incomplete information for use with sequential input classifiers ', associate supervisor.
- Master’s student, University of Tasmania, 'Application of Neural Network Classifiers to Electrocardiographic Body Surface Mapping ', associate supervisor.
- Artificial intelligence and machine learning
- Research methods
Specialist roles
- Associate Dean, Research, Institute of Innovation, Science and Sustainability
- Chair, Federation University AI in Research Working Group
Professional association memberships
- Future of Life Institute’s Existential AI Risk research community
- Ballarat Regional AI Network Advisory Board
Centre for Smart Analytics (CSA)
Peter is part of the Centre for Smart Analytics (CSA), which aims to develop new knowledge and innovative solutions to develop smart and resilient cities, regions and industries.
Health Innovation and Transformation Centre
Peter is part of the Health Innovation and Transformation Centre, which aims to answer complex global healthcare questions that impact the health and wellbeing of our regional, national and international communities.
- Publications
On Generalization Across Environments In Multi-Objective Reinforcement Learning
An empirical investigation of value-based multi-objective reinforcement learning for stochastic environments
- Journals
- DOI reference: 10.1017/S0269888925100052
AI apology: a critical review of apology in AI systems
- Journals
- DOI reference: 10.1007/s10462-025-11305-8