Current studentsExisting staffContact us
 

Towards efficient deep reinforcement learning in complex and dynamic tasks /

Simple item page
dc.contributor.authorChen, Bin
dc.contributor.schoolUniversity of South Australia. UniSA STEM.
dc.contributor.schoolUniSA STEM
dc.date.issued2024
dc.description1 ethesis (xii, 150 pages) :
dc.descriptioncolour illustrations.
dc.descriptionIncludes bibliographical references (pages 128-142)
dc.description.abstractAs an essential means of achieving generalised AI, deep reinforcement learning (DRL) achieved beyond human performance in many decision-making environments, such as competitive games and navigation tasks, by combining the representational power of deep learning with the decision-making power of reinforcement learning. However, the DRL faces sampling efficiency problems with sparse rewards in complex and dynamic environments because it requires massive interactions with environments under partial observability. Due to this inefficient data sampling issue, it isn’t easy to train a DRL agent to achieve optimal performance even after millions of steps. In addition to the instability of the complex and dynamic environment, the problem of training efficiency due to the increasing agent number is even more severe in multiagent DRL (MARL) learning. This thesis focuses on sparse reward issues in complex tasks, sampling efficiency issues in dynamic tasks and state space explosion issues in large-scale multiagent tasks.
dc.description.dissertationThesis (PhD(Computer and Information Science))--University of South Australia, 2024.
dc.identifier.urihttps://hdl.handle.net/11541.2/41104
dc.language.isoen
dc.provenanceCopyright 2024 Bin Chen.
dc.subjectdeep reinforcement learning;multi-agent deep reinforcement learning;training efficiency
dc.subject.lcshDeep learning (Machine learning)
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshReinforcement learning.
dc.titleTowards efficient deep reinforcement learning in complex and dynamic tasks /
dc.typethesis
dcterms.accessRights506 0#$fstar $2Unrestricted online access
ror.fileinfo12296002430001831 13296002420001831 Chen, Bin - Thesis
ror.mmsid9916926624801831

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Chen, Bin - Thesis_Redacted.pdf
Size:
29.77 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections