Single- and multiobjective reinforcement learning in dynamic adversarial games

- Kurniawan, Budi

Title
Single- and multiobjective reinforcement learning in dynamic adversarial games
Creator
Kurniawan, Budi
Date
2022
Type
Text; Thesis; PhD
Identifier
http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/184074
Identifier
vital:16421
Abstract
This thesis uses reinforcement learning (RL) to address dynamic adversarial games in the context of air combat manoeuvring simulation. A sequential decision problem commonly encountered in the field of operations research, air combat manoeuvring simulation conventionally relied on agent programming methods that required significant domain knowledge to be manually encoded into the simulation environment. These methods are appropriate for determining the effectiveness of existing tactics in different simulated scenarios. However, in order to maximise the advantages provided by new technologies (such as autonomous aircraft), new tactics will need to be discovered. A proven technique for solving sequential decision problems, RL has the potential to discover these new tactics. This thesis explores four RL approaches—tabular, deep, discrete-to-deep and multiobjective— as mechanisms for discovering new behaviours in simulations of air combat manoeuvring. Itimplements and tests several methods for each approach and compares those methods in terms of the learning time, baseline and comparative performances, and implementation complexity. In addition to evaluating the utility of existing approaches to the specific task of air combat manoeuvring, this thesis proposes and investigates two novel methods, discrete-to-deep supervised policy learning (D2D-SPL) and discrete-to-deep supervised Q-value learning (D2D-SQL), which can be applied more generally. D2D-SPL and D2D-SQL offer the generalisability of deep RL at a cost closer to the tabular approach.; Doctor of Philosophy
Publisher
Federation University Australia
Rights
All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
Rights
Copyright Budi Kurniawan
Rights
Open Access
Subject
Deep reinforcement; Learning adversarial games air-combat
Full Text
Thesis Supervisor
Vamplew, Peter
  • Hits: 724
  • Visitors: 478
  • Downloads: 57
Thumbnail File Description Size Format
SOURCE2 Australian Digital Thesis 6 MB Adobe Acrobat PDF