P
Peter Vamplew
Researcher at Federation University Australia
Publications - 78
Citations - 2468
Peter Vamplew is an academic researcher from Federation University Australia. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 17, co-authored 68 publications receiving 1506 citations. Previous affiliations of Peter Vamplew include University of Tasmania & Hobart Corporation.
Papers
More filters
Journal ArticleDOI
Survey of intrusion detection systems: techniques, datasets and challenges
TL;DR: A taxonomy of contemporary IDS is presented, a comprehensive review of notable recent works, and an overview of the datasets commonly used for evaluation purposes are presented, and evasion techniques used by attackers to avoid detection are presented.
Journal ArticleDOI
A survey of multi-objective sequential decision-making
TL;DR: This article surveys algorithms designed for sequential decision-making problems with multiple objectives and proposes a taxonomy that classifies multi-objective methods according to the applicable scenario, the nature of the scalarization function, and the type of policies considered.
Journal ArticleDOI
Empirical evaluation methods for multiobjective reinforcement learning algorithms
TL;DR: Standard methods for empirical evaluation of multiobjective reinforcement learning algorithms are proposed, and appropriate evaluation metrics and methodologies are proposed for each class.
Journal ArticleDOI
A novel ensemble of hybrid intrusion detection system for detecting internet of things attacks
TL;DR: The proposed HIDS is evaluated using the Bot-IoT dataset, which includes legitimate IoT network traffic and several types of attacks, and shows that the proposed hybrid IDS provide higher detection rate and lower false positive rate compared to the SIDS and AIDS techniques.
Book ChapterDOI
On the Limitations of Scalarisation for Multi-objective Reinforcement Learning of Pareto Fronts
TL;DR: This paper argues for designing MORL systems to produce a set of solutions approximating the Pareto front, and shows that the common MORL technique of scalarisation has fundamental limitations when used to find Pare to-optimal policies.