Skip navigation
Skip navigation

Designing Curriculum for Deep Reinforcement Learning in StarCraft II

Hao, Daniel; Sweetser Kyburz, Penny; Aitchison, Matthew

Description

Reinforcement learning (RL) has proven successful in games, but suffers from long training times when compared to other forms of machine learning. Curriculum learning, an optimisation technique that improves a model’s ability to learn by presenting training samples in a meaningful order, known as curricula, could offer a solution. Curricula are usually designed manually, due to limitations involved with automating curricula generation. However, as there is a lack of research into effective...[Show more]

CollectionsANU Research Publications
Date published: 2020-11
Type: Conference paper
URI: http://hdl.handle.net/1885/213263
Book Title: AI 2020: Advances in Artificial Intelligence
33rd Australasian Joint Conference, AI 2020, Canberra, ACT, Australia, November 29–30, 2020, Proceedings
DOI: 10.1007/978-3-030-64984-5
Access Rights: Open Access after embargo

Download

File Description SizeFormat Image
SC2_Curriculum_Learning.pdfpaper232.3 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator